In drug discovery, one of the most important tasks is to find novel and biologically active molecules. Given that only a tip of iceberg of drugs was founded in nearly one-century's experimental exploration, it shows great significance to use in silico methods to expand chemical database and profile drug-target linkages. In this study, a web server named ChemGenerator was proposed to generate novel activates for specific targets based on users' input. The ChemGenerator relies on an autoencoder-based algorithm of Recurrent Neural Networks with Long Short-Term Memory by training of 7 million of molecular Simplified Molecular-Input Line-Entry System as the basic model, and further develops target guided generation by transfer learning. As results, ChemGenerator gains lower loss (<0.01) than existing reference model (0.2~0.4) and shows good performance in the case of Epidermal Growth Factor Receptor. Meanwhile, ChemGenerator is now freely accessible to the public by http://smiles.tcmobile.org. In proportion to endless molecular enumeration and time-consuming expensive experiments, this work demonstrates an efficient alternative way for the first virtual screening in drug discovery.

Drug repositioning has received increased attention since the past decade as several blockbuster drugs have come out of repositioning. Computational approaches are significantly contributing to these efforts, of which, network-based methods play a key role. Various structural (topological) network measures have thereby contributed to uncovering unintuitive functional relationships and repositioning candidates in drug-disease and other networks. This review gives a broad overview of the topic, and offers perspectives on the application of topological measures for network analysis. It also discusses unexplored measures, and draws attention to a wider scope of application efforts, especially in drug repositioning.

The studies on relationships between non-coding RNAs and diseases are widely carried out in recent years. A large number of experimental methods and technologies of producing biological data have also been developed. However, due to their high labor cost and production time, nowadays, calculation-based methods, especially machine learning and deep learning methods, have received a lot of attention and been used commonly to solve these problems. From a computational point of view, this survey mainly introduces three common non-coding RNAs, i.e. miRNAs, lncRNAs and circRNAs, and the related computational methods for predicting their association with diseases. First, the mainstream databases of above three non-coding RNAs are introduced in detail. Then, we present several methods for RNA similarity and disease similarity calculations. Later, we investigate ncRNA-disease prediction methods in details and classify these methods into five types: network propagating, recommend system, matrix completion, machine learning and deep learning. Furthermore, we provide a summary of the applications of these five types of computational methods in predicting the associations between diseases and miRNAs, lncRNAs and circRNAs, respectively. Finally, the advantages and limitations of various methods are identified, and future researches and challenges are also discussed.

Protein complexes play important roles in most cellular processes. The available genome-wide protein-protein interaction (PPI) data make it possible for computational methods identifying protein complexes from PPI networks. However, PPI datasets usually contain a large ratio of false positive noise. Moreover, different types of biomolecules in a living cell cooperate to form a union interaction network. Because previous computational methods focus only on PPIs ignoring other types of biomolecule interactions, their predicted protein complexes often contain many false positive proteins. In this study, we develop a novel computational method idenPC-CAP to identify protein complexes from the RNA-protein heterogeneous interaction network consisting of RNA-RNA interactions, RNA-protein interactions and PPIs. By considering interactions among proteins and RNAs, the new method reduces the ratio of false positive proteins in predicted protein complexes. The experimental results demonstrate that idenPC-CAP outperforms the other state-of-the-art methods in this field.

The spatial distribution of proteome at subcellular levels provides clues for protein functions, thus is important to human biology and medicine. Imaging-based methods are one of the most important approaches for predicting protein subcellular location. Although deep neural networks have shown impressive performance in a number of imaging tasks, its application to protein subcellular localization has not been sufficiently explored. In this study, we developed a deep imaging-based approach to localize the proteins at subcellular levels. Based on deep image features extracted from convolutional neural networks (CNNs), both single-label and multi-label locations can be accurately predicted. Particularly, the multi-label prediction is quite a challenging task. Here we developed a criterion learning strategy to exploit the label-attribute relevancy and label-label relevancy. A criterion that was used to determine the final label set was automatically obtained during the learning procedure. We concluded an optimal CNN architecture that could give the best results. Besides, experiments show that compared with the hand-crafted features, the deep features present more accurate prediction with less features. The implementation for the proposed method is available at https://github.com/RanSuLab/ProteinSubcellularLocation.

The accurate quantification of tumor-infiltrating immune cells turns crucial to uncover their role in tumor immune escape, to determine patient prognosis and to predict response to immune checkpoint blockade. Current state-of-the-art methods that quantify immune cells from tumor biopsies using gene expression data apply computational deconvolution methods that present multicollinearity and estimation errors resulting in the overestimation or underestimation of the diversity of infiltrating immune cells and their quantity. To overcome such limitations, we developed MIXTURE, a new ν-support vector regression-based noise constrained recursive feature selection algorithm based on validated immune cell molecular signatures. MIXTURE provides increased robustness to cell type identification and proportion estimation, outperforms the current methods, and is available to the wider scientific community. We applied MIXTURE to transcriptomic data from tumor biopsies and found relevant novel associations between the components of the immune infiltrate and molecular subtypes, tumor driver biomarkers, tumor mutational burden, microsatellite instability, intratumor heterogeneity, cytolytic score, programmed cell death ligand 1 expression, patients' survival and response to anti-cytotoxic T-lymphocyte-associated antigen 4 and anti-programmed cell death protein 1 immunotherapy.

Erectile dysfunction (ED) can be caused by different diseases and controlled by several genetic networks. In this study, to identify the genes related to ED, the expression profiles of normal and ED samples were investigated by the Gene Expression Omnibus (GEO) database. Seventeen genes were identified as associated genes with ED. The protein and nucleic acid sequences of selected genes were retrieved from the UCSC database. Selected genes were diverse according to their physicochemical properties and functions. Category function revealed that selected genes are involved in pathways related to humans some diseases. Furthermore, based on protein interactions, genes associated with the insulin pathway had the greatest interaction with the studied genes. To identify the common cis-regulatory elements, the promoter site of the selected genes was retrieved from the UCSC database. The Gapped Local Alignment of Motifs tool was used for finding common conserved motifs into the promoter site of selected genes. Besides, INSR protein as an insulin receptor precursor showed a high potential site for posttranslation modifications, including phosphorylation and N-glycosylation. Also, in this study, two Guanine-Cytosine (GC)-rich regions were identified as conserved motifs in the upstream of studied genes which can be involved in regulating the expression of genes associated with ED. Also, the conserved binding site of miR-29-3p that is involved in various cancers was observed in the 3' untranslated region of genes associated with ED. Our study introduced new genes associated with ED, which can be good candidates for further analyzing related to human ED.

Single-cell RNA sequencing (scRNA-seq) has enabled researchers to study gene expression at the cellular level. However, due to the extremely low levels of transcripts in a single cell and technical losses during reverse transcription, gene expression at a single-cell resolution is usually noisy and highly dimensional; thus, statistical analyses of single-cell data are a challenge. Although many scRNA-seq data analysis tools are currently available, a gold standard pipeline is not available for all datasets. Therefore, a general understanding of bioinformatics and associated computational issues would facilitate the selection of appropriate tools for a given set of data. In this review, we provide an overview of the goals and most popular computational analysis tools for the quality control, normalization, imputation, feature selection and dimension reduction of scRNA-seq data.

Anti-cancer peptides (ACPs) are known as potential therapeutics for cancer. Due to their unique ability to target cancer cells without affecting healthy cells directly, they have been extensively studied. Many peptide-based drugs are currently evaluated in the preclinical and clinical trials. Accurate identification of ACPs has received considerable attention in recent years; as such, a number of machine learning-based methods for in silico identification of ACPs have been developed. These methods promote the research on the mechanism of ACPs therapeutics against cancer to some extent. There is a vast difference in these methods in terms of their training/testing datasets, machine learning algorithms, feature encoding schemes, feature selection methods and evaluation strategies used. Therefore, it is desirable to summarize the advantages and disadvantages of the existing methods, provide useful insights and suggestions for the development and improvement of novel computational tools to characterize and identify ACPs. With this in mind, we firstly comprehensively investigate 16 state-of-the-art predictors for ACPs in terms of their core algorithms, feature encoding schemes, performance evaluation metrics and webserver/software usability. Then, comprehensive performance assessment is conducted to evaluate the robustness and scalability of the existing predictors using a well-prepared benchmark dataset. We provide potential strategies for the model performance improvement. Moreover, we propose a novel ensemble learning framework, termed ACPredStackL, for the accurate identification of ACPs. ACPredStackL is developed based on the stacking ensemble strategy combined with SVM, Naïve Bayesian, lightGBM and KNN. Empirical benchmarking experiments against the state-of-the-art methods demonstrate that ACPredStackL achieves a comparative performance for predicting ACPs. The webserver and source code of ACPredStackL is freely available at http://bigdata.biocie.cn/ACPredStackL/ and https://github.com/liangxiaoq/ACPredStackL, respectively.

Identifying the types of body fluids left at the crime scene can be essential to reconstructing the crime scene and inferring criminal behavior. MicroRNA (miRNA) molecule extracted from the trace of body fluids is one of the most promising biomarkers for the identification due to its high expression, extreme stability and tissue specificity. However, the detection of miRNA markers is not the answer to a yes-no question but the probability of an assumption. Therefore, it is a crucial task to develop complicated methods combining multi-miRNAs as well as computational algorithms to achieve the goal. In this study, we systematically analyzed the expression of 10 most probable body fluid-specific miRNA markers (miR-451a, miR-205-5p, miR-203a-3p, miR-214-3p, miR-144-3p, miR-144-5p, miR-654-5p, miR-888-5p, miR-891a-5p and miR-124-3p) in 605 body fluids-related samples, including peripheral blood, menstrual blood, saliva, semen and vaginal secretion. We introduced the kernel density estimation (KDE) method and six well-established methods to classify the body fluids in order to find the most optimal combinations of miRNA markers as well as the corresponding classifying method. The results show that the combination of miR-451a, miR-891a-5p, miR-144-5p and miR-203a-3p together with KDE can achieve the most accurate and robust performance according to the cross-validation, independent tests and random perturbation tests. This systematic analysis suggests a reference scheme for the identification of body fluids in an accurate and stable manner.

Billions of people are affected by fungal infection worldwide, which is a major cause of morbidity and mortality in humans. Regardless of development in the field of antifungal therapeutics over the last three decades, multidrug resistance and limited efficacy of available antifungal drugs are very prominent and still a great hurdle in the patient treatment. The current antifungal pipeline is dry, which is needed to be strengthened. Although several strategies have been implemented over time to discover novel promising antifungal leads, but very little emphasis has been given to address the gap of fungal target identification. Undeniably, the need for identifying novel cellular fungal targets is as vital as discovering novel antifungal leads and a structural bioinformatics approach could be an effective strategy in this regard. To address the issue, we have performed in silico screening to identify a few potent multiple targeting ligands and their respective antifungal targets. Thus, we offer a perspective on the phenomena of 'target shortage' and least explored 'multiple targeting' being the most underrated challenges in antifungal drug discovery. 'Structural bioinformatics' could be an effective approach in the recognition of new/innovative antifungal target and identification/development of novel antifungal lead molecule aiming multiple molecular targets of the fungal pathogen.

The rapid development of single-cell RNA sequencing (scRNA-Seq) technology provides strong technical support for accurate and efficient analyzing single-cell gene expression data. However, the analysis of scRNA-Seq is accompanied by many obstacles, including dropout events and the curse of dimensionality. Here, we propose the scGMAI, which is a new single-cell Gaussian mixture clustering method based on autoencoder networks and the fast independent component analysis (FastICA). Specifically, scGMAI utilizes autoencoder networks to reconstruct gene expression values from scRNA-Seq data and FastICA is used to reduce the dimensions of reconstructed data. The integration of these computational techniques in scGMAI leads to outperforming results compared to existing tools, including Seurat, in clustering cells from 17 public scRNA-Seq datasets. In summary, scGMAI is an effective tool for accurately clustering and identifying cell types from scRNA-Seq data and shows the great potential of its applicative power in scRNA-Seq data analysis. The source code is available at https://github.com/QUST-AIBBDRC/scGMAI/.

MOTIVATION: Advances in next-generation sequencing have made it possible to carry out transcriptomic studies at single-cell resolution and generate vast amounts of single-cell RNA sequencing (RNA-seq) data rapidly. Thus, tools to analyze this data need to evolve as well as to improve accuracy and efficiency. RESULTS: We present FEATS, a Python software package, that performs clustering on single-cell RNA-seq data. FEATS is capable of performing multiple tasks such as estimating the number of clusters, conducting outlier detection and integrating data from various experiments. We develop a univariate feature selection-based approach for clustering, which involves the selection of top informative features to improve clustering performance. This is motivated by the fact that cell types are often manually determined using the expression of only a few known marker genes. On a variety of single-cell RNA-seq datasets, FEATS gives superior performance compared with the current tools, in terms of adjusted Rand index and estimating the number of clusters. It achieves a 22% improvement in clustering and more accurately estimates the number of clusters when compared with other tools. In addition to cluster estimation, FEATS also performs outlier detection and data integration while giving an excellent computational performance. Thus, FEATS is a comprehensive clustering tool capable of addressing the challenges during the clustering of single-cell RNA-seq data. AVAILABILITY: The installation instructions and documentation of FEATS is available at https://edwinv87.github.io/feats/. SUPPLEMENTARY DATA: Supplementary data are available online at https://academic.oup.com/bib.

Unsupervised methods, such as clustering methods, are essential to the analysis of single-cell genomic data. The most current clustering methods are designed for one data type only, such as single-cell RNA sequencing (scRNA-seq), single-cell ATAC sequencing (scATAC-seq) or sc-methylation data alone, and a few are developed for the integrative analysis of multiple data types. The integrative analysis of multimodal single-cell genomic data sets leverages the power in multiple data sets and can deepen the biological insight. In this paper, we propose a coupled co-clustering-based unsupervised transfer learning algorithm (coupleCoC) for the integrative analysis of multimodal single-cell data. Our proposed coupleCoC builds upon the information theoretic co-clustering framework. In co-clustering, both the cells and the genomic features are simultaneously clustered. Clustering similar genomic features reduces the noise in single-cell data and facilitates transfer of knowledge across single-cell datasets. We applied coupleCoC for the integrative analysis of scATAC-seq and scRNA-seq data, sc-methylation and scRNA-seq data and scRNA-seq data from mouse and human. We demonstrate that coupleCoC improves the overall clustering performance and matches the cell subpopulations across multimodal single-cell genomic datasets. Our method coupleCoC is also computationally efficient and can scale up to large datasets. Availability: The software and datasets are available at https://github.com/cuhklinlab/coupleCoC.

MOTIVATION: Estimating microbial association networks from high-throughput sequencing data is a common exploratory data analysis approach aiming at understanding the complex interplay of microbial communities in their natural habitat. Statistical network estimation workflows comprise several analysis steps, including methods for zero handling, data normalization and computing microbial associations. Since microbial interactions are likely to change between conditions, e.g. between healthy individuals and patients, identifying network differences between groups is often an integral secondary analysis step. Thus far, however, no unifying computational tool is available that facilitates the whole analysis workflow of constructing, analysing and comparing microbial association networks from high-throughput sequencing data. RESULTS: Here, we introduce NetCoMi (Network Construction and comparison for Microbiome data), an R package that integrates existing methods for each analysis step in a single reproducible computational workflow. The package offers functionality for constructing and analysing single microbial association networks as well as quantifying network differences. This enables insights into whether single taxa, groups of taxa or the overall network structure change between groups. NetCoMi also contains functionality for constructing differential networks, thus allowing to assess whether single pairs of taxa are differentially associated between two groups. Furthermore, NetCoMi facilitates the construction and analysis of dissimilarity networks of microbiome samples, enabling a high-level graphical summary of the heterogeneity of an entire microbiome sample collection. We illustrate NetCoMi's wide applicability using data sets from the GABRIELA study to compare microbial associations in settled dust from children's rooms between samples from two study centers (Ulm and Munich). AVAILABILITY: R scripts used for producing the examples shown in this manuscript are provided as supplementary data. The NetCoMi package, together with a tutorial, is available at https://github.com/stefpeschel/NetCoMi. CONTACT: Tel:+49 89 3187 43258; stefanie.peschel@mail.de. SUPPLEMENTARY INFORMATION: Supplementary data are available at Briefings in Bioinformatics online.

Deconvolution of mouse transcriptomic data is challenged by the fact that mouse models carry various genetic and physiological perturbations, making it questionable to assume fixed cell types and cell type marker genes for different data set scenarios. We developed a Semi-Supervised Mouse data Deconvolution (SSMD) method to study the mouse tissue microenvironment. SSMD is featured by (i) a novel nonparametric method to discover data set-specific cell type signature genes; (ii) a community detection approach for fixing cell types and their marker genes; (iii) a constrained matrix decomposition method to solve cell type relative proportions that is robust to diverse experimental platforms. In summary, SSMD addressed several key challenges in the deconvolution of mouse tissue data, including: (i) varied cell types and marker genes caused by highly divergent genotypic and phenotypic conditions of mouse experiment; (ii) diverse experimental platforms of mouse transcriptomics data; (iii) small sample size and limited training data source and (iv) capable to estimate the proportion of 35 cell types in blood, inflammatory, central nervous or hematopoietic systems. In silico and experimental validation of SSMD demonstrated its high sensitivity and accuracy in identifying (sub) cell types and predicting cell proportions comparing with state-of-the-arts methods. A user-friendly R package and a web server of SSMD are released via https://github.com/xiaoyulu95/SSMD.

BACKGROUND: Fluorescent detection methods are indispensable tools for chemical biology. However, the frequent appearance of potential fluorescent compound has greatly interfered with the recognition of compounds with genuine activity. Such fluorescence interference is especially difficult to identify as it is reproducible and possesses concentration-dependent characteristic. Therefore, the development of a credible screening tool to detect fluorescent compounds from chemical libraries is urgently needed in early stages of drug discovery. RESULTS: In this study, we developed a webserver ChemFLuo for fluorescent compound detection, based on two large and high-quality training datasets containing 4906 blue and 8632 green fluorescent compounds. These molecules were used to construct a group of prediction models based on the combination of three machine learning algorithms and seven types of molecular representations. The best blue fluorescence prediction model achieved with balanced accuracy (BA) = 0.858 and area under the receiver operating characteristic curve (AUC) = 0.931 for the validation set, and BA = 0.823 and AUC = 0.903 for the test set. The best green fluorescence prediction model achieved the prediction accuracy with BA = 0.810 and AUC = 0.887 for the validation set, and BA = 0.771 and AUC = 0.852 for the test set. Besides prediction model, 22 blue and 16 green representative fluorescent substructures were summarized for the screening of potential fluorescent compounds. The comparison with other fluorescence detection tools and theapplication to external validation sets and large molecule libraries have demonstrated the reliability of prediction model for fluorescent compound detection. CONCLUSION: ChemFLuo is a public webserver to filter out compounds with undesirable fluorescent properties, which will benefit the design of high-quality chemical libraries for drug discovery. It is freely available at http://admet.scbdd.com/chemfluo/index/.

The prevalence of dropout events is a serious problem for single-cell Hi-C (scHiC) data due to insufficient sequencing depth and data coverage, which brings difficulties in downstream studies such as clustering and structural analysis. Complicating things further is the fact that dropouts are confounded with structural zeros due to underlying properties, leading to observed zeros being a mixture of both types of events. Although a great deal of progress has been made in imputing dropout events for single cell RNA-sequencing (RNA-seq) data, little has been done in identifying structural zeros and imputing dropouts for scHiC data. In this paper, we adapted several methods from the single-cell RNA-seq literature for inference on observed zeros in scHiC data and evaluated their effectiveness. Through an extensive simulation study and real data analysis, we have shown that a couple of the adapted single-cell RNA-seq algorithms can be powerful for correctly identifying structural zeros and accurately imputing dropout values. Downstream analysis using the imputed values showed considerable improvement for clustering cells of the same types together over clustering results before imputation.

Autophagy plays a crucial role in maintaining cellular homeostasis through the degradation of unwanted materials like damaged mitochondria and misfolded proteins. However, the contribution of autophagy toward a healthy cell environment is not only limited to the cleaning process. It also assists in protein synthesis when the system lacks the amino acids' inflow from the extracellular environment due to diet consumptions. Reduction in the autophagy process is associated with diseases like cancer, diabetes, non-alcoholic steatohepatitis, etc., while uncontrolled autophagy may facilitate cell death. We need a better understanding of the autophagy processes and their regulatory mechanisms at various levels (molecules, cells, tissues). This demands a thorough understanding of the system with the help of mathematical and computational tools. The present review illuminates how systems biology approaches are being used for the study of the autophagy process. A comprehensive insight is provided on the application of computational methods involving mathematical modeling and network analysis in the autophagy process. Various mathematical models based on the system of differential equations for studying autophagy are covered here. We have also highlighted the significance of network analysis and machine learning in capturing the core regulatory machinery governing the autophagy process. We explored the available autophagic databases and related resources along with their attributes that are useful in investigating autophagy through computational methods. We conclude the article addressing the potential future perspective in this area, which might provide a more in-depth insight into the dynamics of autophagy.

Simultaneous profiling transcriptomic and chromatin accessibility information in the same individual cells offers an unprecedented resolution to understand cell states. However, computationally effective methods for the integration of these inherent sparse and heterogeneous data are lacking. Here, we present a single-cell multimodal variational autoencoder model, which combines three types of joint-learning strategies with a probabilistic Gaussian Mixture Model to learn the joint latent features that accurately represent these multilayer profiles. Studies on both simulated datasets and real datasets demonstrate that it has more preferable capability (i) dissecting cellular heterogeneity in the joint-learning space, (ii) denoising and imputing data and (iii) constructing the association between multilayer omics data, which can be used for understanding transcriptional regulatory mechanisms.

BACKGROUND: A mass spectrometry-based assessment of methicillin resistance in Staphylococcus aureus would have huge potential in addressing fast and effective prediction of antibiotic resistance. Since delays in the traditional antibiotic susceptibility testing, methicillin-resistant S. aureus remains a serious threat to human health. RESULTS: Here, linking a 7 years of longitudinal study from two cohorts in the Taiwan area of over 20 000 individually resolved methicillin susceptibility testing results, we identify associations of methicillin resistance with the demographics and mass spectrometry data. When combined together, these connections allow for machine-learning-based predictions of methicillin resistance, with an area under the receiver operating characteristic curve of >0.85 in both the discovery [95% confidence interval (CI) 0.88-0.90] and replication (95% CI 0.84-0.86) populations. CONCLUSIONS: Our predictive model facilitates early detection for methicillin resistance of patients with S. aureus infection. The large-scale antibiotic resistance study has unbiasedly highlighted putative candidates that could improve trials of treatment efficiency and inform on prescriptions.

Erratum in Brief Bioinform. 2021 Sep 2;22(5):

Time-course RNAseq experiments, where tissues are repeatedly collected from the same subjects, e.g. humans or animals over time or under several different experimental conditions, are becoming more popular due to the reducing sequencing costs. Such designs offer the great potential to identify genes that change over time or progress differently in time across experimental groups. Modelling of the longitudinal gene expression in such time-course RNAseq data is complicated by the serial correlations, missing values due to subject dropout or sequencing errors, long follow up with potentially non-linear progression in time and low number of subjects. Negative Binomial mixed models can address all these issues. However, such models under the maximum likelihood (ML) approach are less popular for RNAseq data due to convergence issues (see, e.g. [1]). We argue in this paper that it is the use of an inaccurate numerical integration method in combination with the typically small sample sizes which causes such mixed models to fail for a great portion of tested genes. We show that when we use the accurate adaptive Gaussian quadrature approach to approximate the integrals over the random-effects terms, we can successfully estimate the model parameters with the maximum likelihood method. Moreover, we show that the boostrap method can be used to preserve the type I error rate in small sample settings. We evaluate empirically the small sample properties of the test statistics and compare with state-of-the-art approaches. The method is applied on a longitudinal mice experiment to study the dynamics in Duchenne Muscular Dystrophy. Contact:s.tsonaka@lumc.nl Roula Tsonaka is an assistant professor at the Medical Statistics, Department of Biomedical Data Sciences, Leiden University Medical Center. Her research focuses on statistical methods for longitudinal omics data. Pietro Spitali is an assistant professor at the Department of Human Genetics, Leiden University Medical Center. His research focuses on the identification of biomarkers for neuromuscular disorders.

Alternative polyadenylation (APA) generates diverse mRNA isoforms, which contributes to transcriptome diversity and gene expression regulation by affecting mRNA stability, translation and localization in cells. The rapid development of 3' tag-based single-cell RNA-sequencing (scRNA-seq) technologies, such as CEL-seq and 10x Genomics, has led to the emergence of computational methods for identifying APA sites and profiling APA dynamics at single-cell resolution. However, existing methods fail to detect the precise location of poly(A) sites or sites with low read coverage. Moreover, they rely on priori genome annotation and can only detect poly(A) sites located within or near annotated genes. Here we proposed a tool called scAPAtrap for detecting poly(A) sites at the whole genome level in individual cells from 3' tag-based scRNA-seq data. scAPAtrap incorporates peak identification and poly(A) read anchoring, enabling the identification of the precise location of poly(A) sites, even for sites with low read coverage. Moreover, scAPAtrap can identify poly(A) sites without using priori genome annotation, which helps locate novel poly(A) sites in previously overlooked regions and improve genome annotation. We compared scAPAtrap with two latest methods, scAPA and Sierra, using scRNA-seq data from different experimental technologies and species. Results show that scAPAtrap identified poly(A) sites with higher accuracy and sensitivity than competing methods and could be used to explore APA dynamics among cell types or the heterogeneous APA isoform expression in individual cells. scAPAtrap is available at https://github.com/BMILAB/scAPAtrap.

The identification of hidden responders is often an essential challenge in precision oncology. A recent attempt based on machine learning has been proposed for classifying aberrant pathway activity from multiomic cancer data. However, we note several critical limitations there, such as high-dimensionality, data sparsity and model performance. Given the central importance and broad impact of precision oncology, we propose nature-inspired deep Ras activation pan-cancer (NatDRAP), a deep neural network (DNN) model, to address those restrictions for the identification of hidden responders. In this study, we develop the nature-inspired deep learning model that integrates bulk RNA sequencing, copy number and mutation data from PanCanAltas to detect pan-cancer Ras pathway activation. In NatDRAP, we propose to synergize the nature-inspired artificial bee colony algorithm with different gradient-based optimizers in one framework for optimizing DNNs in a collaborative manner. Multiple experiments were conducted on 33 different cancer types across PanCanAtlas. The experimental results demonstrate that the proposed NatDRAP can provide superior performance over other benchmark methods with strong robustness towards diagnosing RAS aberrant pathway activity across different cancer types. In addition, gene ontology enrichment and pathological analysis are conducted to reveal novel insights into the RAS aberrant pathway activity identification and characterization. NatDRAP is written in Python and available at https://github.com/lixt314/NatDRAP1.

As a newly discovered protein posttranslational modification, histone lysine crotonylation (Kcr) involved in cellular regulation and human diseases. Various proteomics technologies have been developed to detect Kcr sites. However, experimental approaches for identifying Kcr sites are often time-consuming and labor-intensive, which is difficult to widely popularize in large-scale species. Computational approaches are cost-effective and can be used in a high-throughput manner to generate relatively precise identification. In this study, we develop a deep learning-based method termed as Deep-Kcr for Kcr sites prediction by combining sequence-based features, physicochemical property-based features and numerical space-derived information with information gain feature selection. We investigate the performances of convolutional neural network (CNN) and five commonly used classifiers (long short-term memory network, random forest, LogitBoost, naive Bayes and logistic regression) using 10-fold cross-validation and independent set test. Results show that CNN could always display the best performance with high computational efficiency on large dataset. We also compare the Deep-Kcr with other existing tools to demonstrate the excellent predictive power and robustness of our method. Based on the proposed model, a webserver called Deep-Kcr was established and is freely accessible at http://lin-group.cn/server/Deep-Kcr.

Single-cell mRNA sequencing has been adopted as a powerful technique for understanding gene expression profiles at the single-cell level. However, challenges remain due to factors such as the inefficiency of mRNA molecular capture, technical noises and separate sequencing of cells in different batches. Normalization methods have been developed to ensure a relatively accurate analysis. This work presents a survey on 10 tools specifically designed for single-cell mRNA sequencing data preprocessing steps, among which 6 tools are used for dropout normalization and 4 tools are for batch effect correction. In this survey, we outline the main methodology for each of these tools, and we also compare these tools to evaluate their normalization performance on datasets which are simulated under the constraints of dropout inefficiency, batch effect or their combined effects. We found that Saver and Baynorm performed better than other methods in dropout normalization, in most cases. Beer and Batchelor performed better in the batch effect normalization, and the Saver-Beer tool combination and the Baynorm-Beer combination performed better in the mixed dropout-and-batch effect normalization. Over-normalization is a common issue occurred to these dropout normalization tools that is worth of future investigation. For the batch normalization tools, the capability of retaining heterogeneity between different groups of cells after normalization can be another direction for future improvement.

Least absolute shrinkage and selection operator (LASSO) regression is often applied to select the most promising set of single nucleotide polymorphisms (SNPs) associated with a molecular phenotype of interest. While the penalization parameter λ restricts the number of selected SNPs and the potential model overfitting, the least-squares loss function of standard LASSO regression translates into a strong dependence of statistical results on a small number of individuals with phenotypes or genotypes divergent from the majority of the study population-typically comprised of outliers and high-leverage observations. Robust methods have been developed to constrain the influence of divergent observations and generate statistical results that apply to the bulk of study data, but they have rarely been applied to genetic association studies. In this article, we review, for newcomers to the field of robust statistics, a novel version of standard LASSO that utilizes the Huber loss function. We conduct comprehensive simulations and analyze real protein, metabolite, mRNA expression and genotype data to compare the stability of penalization, the cross-iteration concordance of the model, the false-positive and true-positive rates and the prediction accuracy of standard and robust Huber-LASSO. Although the two methods showed controlled false-positive rates ≤2.1% and similar true-positive rates, robust Huber-LASSO outperformed standard LASSO in the accuracy of predicted protein, metabolite and gene expression levels using individual SNP data. The conducted simulations and real-data analyses show that robust Huber-LASSO represents a valuable alternative to standard LASSO in genetic studies of molecular phenotypes.

The DNA methyltransferases (DNMTs) (DNMT3A, DNMT3B and DNMT3L) are primarily responsible for the establishment of genomic locus-specific DNA methylation patterns, which play an important role in gene regulation and animal development. However, this important protein family's binding mechanism, i.e. how and where the DNMTs bind to genome, is still missing in most tissues and cell lines. This motivates us to explore DNMTs and TF's cooperation and develop a network regularized logistic regression model, GuidingNet, to predict DNMTs' genome-wide binding by integrating gene expression, chromatin accessibility, sequence and protein-protein interaction data. GuidingNet accurately predicted methylation experimental data validated DNMTs' binding, outperformed single data source based and sparsity regularized methods and performed well in within and across tissue prediction for several DNMTs in human and mouse. Importantly, GuidingNet can reveal transcription cofactors assisting DNMTs for methylation establishment. This provides biological understanding in the DNMTs' binding specificity in different tissues and demonstrate the advantage of network regularization. In addition to DNMTs, GuidingNet achieves good performance for other chromatin regulators' binding. GuidingNet is freely available at https://github.com/AMSSwanglab/GuidingNet.

Single-cell RNA-sequencing (scRNA-seq) data widely exist in bioinformatics. It is crucial to devise a distance metric for scRNA-seq data. Almost all existing clustering methods based on spectral clustering algorithms work in three separate steps: similarity graph construction; continuous labels learning; discretization of the learned labels by k-means clustering. However, this common practice has potential flaws that may lead to severe information loss and degradation of performance. Furthermore, the performance of a kernel method is largely determined by the selected kernel; a self-weighted multiple kernel learning model can help choose the most suitable kernel for scRNA-seq data. To this end, we propose to automatically learn similarity information from data. We present a new clustering method in the form of a multiple kernel combination that can directly discover groupings in scRNA-seq data. The main proposition is that automatically learned similarity information from scRNA-seq data is used to transform the candidate solution into a new solution that better approximates the discrete one. The proposed model can be efficiently solved by the standard support vector machine (SVM) solvers. Experiments on benchmark scRNA-Seq data validate the superior performance of the proposed model. Spectral clustering with multiple kernels is implemented in Matlab, licensed under Massachusetts Institute of Technology (MIT) and freely available from the Github website, https://github.com/Cuteu/SMSC/.

Due to the high cost of flow and mass cytometry, there has been a recent surge in the development of computational methods for estimating the relative distributions of cell types from the gene expression profile of a bulk of cells. Here, we review the five common 'digital cytometry' methods: deconvolution of RNA-Seq, cell-type identification by estimating relative subsets of RNA transcripts (CIBERSORT), CIBERSORTx, single sample gene set enrichment analysis and single-sample scoring of molecular phenotypes deconvolution method. The results show that CIBERSORTx B-mode, which uses batch correction to adjust the gene expression profile of the bulk of cells ('mixture data') to eliminate possible cross-platform variations between the mixture data and the gene expression data of single cells ('signature matrix'), outperforms other methods, especially when signature matrix and mixture data come from different platforms. However, in our tests, CIBERSORTx S-mode, which uses batch correction for adjusting the signature matrix instead of mixture data, did not perform better than the original CIBERSORT method, which does not use any batch correction method. This result suggests the need for further investigations into how to utilize batch correction in deconvolution methods.

Emerging evidence indicates that the abnormal expression of miRNAs involves in the evolution and progression of various human complex diseases. Identifying disease-related miRNAs as new biomarkers can promote the development of disease pathology and clinical medicine. However, designing biological experiments to validate disease-related miRNAs is usually time-consuming and expensive. Therefore, it is urgent to design effective computational methods for predicting potential miRNA-disease associations. Inspired by the great progress of graph neural networks in link prediction, we propose a novel graph auto-encoder model, named GAEMDA, to identify the potential miRNA-disease associations in an end-to-end manner. More specifically, the GAEMDA model applies a graph neural networks-based encoder, which contains aggregator function and multi-layer perceptron for aggregating nodes' neighborhood information, to generate the low-dimensional embeddings of miRNA and disease nodes and realize the effective fusion of heterogeneous information. Then, the embeddings of miRNA and disease nodes are fed into a bilinear decoder to identify the potential links between miRNA and disease nodes. The experimental results indicate that GAEMDA achieves the average area under the curve of $93.56\pm 0.44\%$ under 5-fold cross-validation. Besides, we further carried out case studies on colon neoplasms, esophageal neoplasms and kidney neoplasms. As a result, 48 of the top 50 predicted miRNAs associated with these diseases are confirmed by the database of differentially expressed miRNAs in human cancers and microRNA deregulation in human disease database, respectively. The satisfactory prediction performance suggests that GAEMDA model could serve as a reliable tool to guide the following researches on the regulatory role of miRNAs. Besides, the source codes are available at https://github.com/chimianbuhetang/GAEMDA.

Comment in Brief Bioinform. 2021 Sep 2;22(5):

Uveal melanoma (UVM) is the most common primary intraocular human malignancy with a high mortality rate. Aberrant DNA methylation has rapidly emerged as a diagnostic and prognostic signature in many cancers. However, such DNA methylation signature available in UVM remains limited. In this study, we performed a genome-wide integrative analysis of methylome and transcriptome and identified 40 methylation-driven prognostic genes (MDPGs) associated with the tumorigenesis and progression of UVM. Then, we proposed a machine-learning-based discovery and validation strategy to identify a DNA methylation-driven signature (10MeSig) composing of 10 MDPGs (AZGP1, BAI1, CCDC74A, FUT3, PLCD1, S100A4, SCN8A, SEMA3B, SLC25A38 and SLC44A3), which stratified 80 patients of the discovery cohort into two risk subtypes with significantly different overall survival (HR = 29, 95% CI: 6.7-126, P < 0.001). The 10MeSig was validated subsequently in an independent cohort with 57 patients and yielded a similar prognostic value (HR = 2.1, 95% CI: 1.2-3.7, P = 0.006). Multivariable Cox regression analysis showed that the 10MeSig is an independent predictive factor for the survival of patients with UVM. With a prospective validation study, this 10MeSig will improve clinical decisions and provide new insights into the pathogenesis of UVM.

Mapping protein-protein interactions at a proteome scale is critical to understanding how cellular signaling networks respond to stimuli. Since eukaryotic genomes encode thousands of proteins, testing their interactions one-by-one is a challenging prospect. High-throughput yeast-two hybrid (Y2H) assays that employ next-generation sequencing to interrogate complementary DNA (cDNA) libraries represent an alternative approach that optimizes scale, cost and effort. We present NGPINT, a robust and scalable software to identify all putative interactors of a protein using Y2H in batch culture. NGPINT combines diverse tools to align sequence reads to target genomes, reconstruct prey fragments and compute gene enrichment under reporter selection. Central to this pipeline is the identification of fusion reads containing sequences derived from both the Y2H expression plasmid and the cDNA of interest. To reduce false positives, these fusion reads are evaluated as to whether the cDNA fragment forms an in-frame translational fusion with the Y2H transcription factor. NGPINT successfully recognized 95% of interactions in simulated test runs. As proof of concept, NGPINT was tested using published data sets and it recognized all validated interactions. NGPINT can process interaction data from any biosystem with an available genome or transcriptome reference, thus facilitating the discovery of protein-protein interactions in model and non-model organisms.

The human cerebral cortex undergoes profound structural and functional dynamic variations across the lifespan, whereas the underlying molecular mechanisms remain unclear. Here, with a novel method transcriptome-connectome correlation analysis (TCA), which integrates the brain functional magnetic resonance images and region-specific transcriptomes, we identify age-specific cortex (ASC) gene signatures for adolescence, early adulthood and late adulthood. The ASC gene signatures are significantly correlated with the cortical thickness (P-value <2.00e-3) and myelination (P-value <1.00e-3), two key brain structural features that vary in accordance with brain development. In addition to the molecular underpinning of age-related brain functions, the ASC gene signatures allow delineation of the molecular mechanisms of neuropsychiatric disorders, such as the regulation between ARNT2 and its target gene ETF1 involved in Schizophrenia. We further validate the ASC gene signatures with published gene sets associated with the adult cortex, and confirm the robustness of TCA on other brain image datasets. Availability: All scripts are written in R. Scripts for the TCA method and related statistics result can be freely accessed at https://github.com/Soulnature/TCA. Additional data related to this paper may be requested from the authors.

Despite gene expression programs being notoriously complex, RNA abundance is usually assumed as a proxy for transcriptional activity. Recently developed approaches, able to disentangle transcriptional and post-transcriptional regulatory processes, have revealed a more complex scenario. It is now possible to work out how synthesis, processing and degradation kinetic rates collectively determine the abundance of each gene's RNA. It has become clear that the same transcriptional output can correspond to different combinations of the kinetic rates. This underscores the fact that markedly different modes of gene expression regulation exist, each with profound effects on a gene's ability to modulate its own expression. This review describes the development of the experimental and computational approaches, including RNA metabolic labeling and mathematical modeling, that have been disclosing the mechanisms underlying complex transcriptional programs. Current limitations and future perspectives in the field are also discussed.

There is a great interest in increasing proteins' stability to widen their usability in numerous biomedical and biotechnological applications. However, native proteins cannot usually withstand the harsh industrial environment, since they are evolved to function under mild conditions. Ancestral sequence reconstruction is a well-established method for deducing the evolutionary history of genes. Besides its applicability to discover the most probable evolutionary ancestors of the modern proteins, ancestral sequence reconstruction has proven to be a useful approach for the design of highly stable proteins. Recently, several computational tools were developed, which make the ancestral reconstruction algorithms accessible to the community, while leaving the most crucial steps of the preparation of the input data on users' side. FireProtASR aims to overcome this obstacle by constructing a fully automated workflow, allowing even the unexperienced users to obtain ancestral sequences based on a sequence query as the only input. FireProtASR is complemented with an interactive, easy-to-use web interface and is freely available at https://loschmidt.chemi.muni.cz/fireprotasr/.

FASTA and FASTQ are the most widely used biological data formats that have become the de facto standard to exchange sequence data between bioinformatics tools. With the avalanche of next-generation sequencing data, the amount of sequence data being deposited and accessed in FASTA/Q formats is increasing dramatically. However, the existing tools have very low efficiency at random retrieval of subsequences due to the requirement of loading the entire index into memory. In addition, most existing tools have no capability to build index for large FASTA/Q files because of the limited memory. Furthermore, the tools do not provide support to randomly accessing sequences from FASTA/Q files compressed by gzip, which is extensively adopted by most public databases to compress data for saving storage. In this study, we developed pyfastx as a versatile Python package with commonly used command-line tools to overcome the above limitations. Compared to other tools, pyfastx yielded the highest performance in terms of building index and random access to sequences, particularly when dealing with large FASTA/Q files with hundreds of millions of sequences. A key advantage of pyfastx over other tools is that it offers an efficient way to randomly extract subsequences directly from gzip compressed FASTA/Q files without needing to uncompress beforehand. Pyfastx can easily be installed from PyPI (https://pypi.org/project/pyfastx) and the source code is freely available at https://github.com/lmdu/pyfastx.

Thyroid nodules are neoplasms commonly found among adults, with papillary thyroid carcinoma (PTC) being the most prevalent malignancy. However, current diagnostic methods often subject patients to unnecessary surgical burden. In this study, we developed and validated an automated, highly accurate multi-study-derived diagnostic model for PTCs using personalized biological pathways coupled with a sophisticated machine learning algorithm. Surprisingly, the algorithm achieved near-perfect performance in discriminating PTCs from non-tumoral thyroid samples with an overall cross-study-validated area under the receiver operating characteristic curve (AUROC) of 0.999 (95% confidence interval [CI]: 0.995-1) and a Brier score of 0.013 on three independent development cohorts. In addition, the algorithm showed excellent generalizability and transferability on two large-scale external blind PTC cohorts consisting of The Cancer Genome Atlas (TCGA), which is the largest genomic PTC cohort studied to date, and the post-Chernobyl cohort, which includes PTCs reported after exposure to radiation from the Chernobyl accident. When applied to the TCGA cohort, the model yielded an AUROC of 0.969 (95% CI: 0.950-0.987) and a Brier score of 0.109. On the post-Chernobyl cohort, it yielded an AUROC of 0.962 (95% CI: 0.918-1) and a Brier score of 0.073. This algorithm also is robust against other various types of clinical scenarios, discriminating malignant from benign lesions as well as clinically aggressive thyroid cancer with poor prognosis from indolent ones. Furthermore, we discovered novel pathway alterations and prognostic signatures for PTC, which can provide directions for follow-up studies.

Chromatin immunoprecipitation followed by next-generation sequencing (ChIP-seq) is recognized as an extremely powerful tool to study the interaction of numerous transcription factors and other chromatin-associated proteins with DNA. The core problem in the optimization of ChIP-seq protocol and the following computational data analysis is that a 'true' pattern of binding events for a given protein factor is unknown. Computer simulation of the ChIP-seq process based on 'a-priory known binding template' can contribute to a drastically reduce the number of wet lab experiments and finally help achieve radical optimization of the entire processing pipeline. We present a newly developed ChIP-sequencing simulation algorithm implemented in the novel software, in silico ChIP-seq (isChIP). We demonstrate that isChIP closely approximates real ChIP-seq protocols and is able to model data similar to those obtained from experimental sequencing. We validated isChIP using publicly available datasets generated for well-characterized transcription factors Oct4 and Sox2. Although the novel software is compatible with the Illumina protocols by default, it can also successfully perform simulations with a number of alternative sequencing platforms such as Roche454, Ion Torrent and SOLiD as well as model ChIP -Exo. The versatility of isChIP was demonstrated through modelling a wide range of binding events, including those of transcription factors and chromatin modifiers. We also performed a comparative analysis against a few existing ChIP-seq simulators and showed the fundamental superiority of our model. Due to its ability to utilize known binding templates, isChIP can potentially be employed to help investigators choose the most appropriate analytical software through benchmarking of available ChIP-seq programs and optimize the experimental parameters of ChIP-seq protocol. isChIP software is freely available at https://github.com/fnaumenko/isChIP.

The genus Culicoides includes biting midges, some of which are vectors for viruses that cause diseases in humans and animals. Knowledge of the roles of Culicoides in viral ecology is inadequate. We collected ~300 000 samples of Culicoides and mosquitoes in 15 representative regions within Yunnan, China. Using mosquitoes as reference vectors, we designed a comparative virome strategy to study the viral composition, diversity, hosts and spatiotemporal distribution of Culicoides. A map of viromes in Culicoides and mosquitoes in Yunan province, China, was constructed. At the same locations, Culicoides and mosquitoes usually share a similar viral diversity. At least 10 important pathogenic viruses were detected from Culicoides. Many novel viruses were discovered, including 21 segmented viruses of Flaviviridae, 180 viruses of Monjiviricetes and 130 viruses of Bunyavirales. The findings demonstrate that Culicoides is an important part of viral ecology and should be studied and monitored for potentially emerging viruses.

The peptide therapeutics market is providing new opportunities for the biotechnology and pharmaceutical industries. Therefore, identifying therapeutic peptides and exploring their properties are important. Although several studies have proposed different machine learning methods to predict peptides as being therapeutic peptides, most do not explain the decision factors of model in detail. In this work, an Interpretable Therapeutic Peptide Prediction (ITP-Pred) model based on efficient feature fusion was developed. First, we proposed three kinds of feature descriptors based on sequence and physicochemical property encoded, namely amino acid composition (AAC), group AAC and coding autocorrelation, and concatenated them to obtain the feature representation of therapeutic peptide. Then, we input it into the CNN-Bi-directional Long Short-Term Memory (BiLSTM) model to automatically learn recognition of therapeutic peptides. The cross-validation and independent verification experiments results indicated that ITP-Pred has a higher prediction performance on the benchmark dataset than other comparison methods. Finally, we analyzed the output of the model from two aspects: sequence order and physical and chemical properties, mining important features as guidance for the design of better models that can complement existing methods.

RNA sequencing data sets rapidly increase in quantity. For microRNAs (miRNAs), frequently dozens to hundreds of billion reads are generated per study. The quantification of annotated miRNAs and the prediction of new miRNAs are leading computational tasks. Now, the increased depth of coverage allows to gain deeper insights into the variability of miRNAs. The analysis of isoforms of miRNAs (isomiRs) is a trending topic, and a range of computational tools for the analysis of isomiRs has been developed. We provide an overview on 27 available computational solutions for the analysis of isomiRs. These include both stand-alone programs (17 tools) and web-based solutions (10 tools) and span a publication time range from 2010 to 2020. Seven of the tools were published in 2019 and 2020, confirming the rising importance of the topic. While most of the analyzed tools work for a broad range of organisms or are completely independent of a reference organism, several tools have been tailored for the analysis of human miRNA data or for plants. While 14 of the tools are general analysis tools of miRNAs, and isomiR analysis is one of their features, the remaining 13 tools have specifically been developed for isomiR analysis. A direct comparison on 20 deep sequencing data sets for selected tools provides insights into the heterogeneity of results. With our work, we provide users a comprehensive overview on the landscape of isomiR analysis tools and in that support the selection of the most appropriate tool for their respective research task.

Breast cancer is one of the most common types of cancers and the leading cause of death from malignancy among women worldwide. Tumor-infiltrating lymphocytes are a source of important prognostic biomarkers for breast cancer patients. In this study, based on the tumor-infiltrating lymphocytes in the tumor immune microenvironment, a risk score prognostic model was developed in the training cohort for risk stratification and prognosis prediction in breast cancer patients. The prognostic value of this risk score prognostic model was also verified in the two testing cohorts and the TCGA pan cancer cohort. Nomograms were also established in the training and testing cohorts to validate the clinical use of this model. Relationships between the risk score, intrinsic molecular subtypes, immune checkpoints, tumor-infiltrating immune cell abundances and the response to chemotherapy and immunotherapy were also evaluated. Based on these results, we can conclude that this risk score model could serve as a robust prognostic biomarker, provide therapeutic benefits for the development of novel chemotherapy and immunotherapy, and may be helpful for clinical decision making in breast cancer patients.

A large amount of omics data and number of bioinformatics tools has been produced. However, the methods for further exploring omics data are simple, in particular, to mine key regulatory genes, which are a priority concern in biological systems, and most of the specific functions are still unknown. First, raw data of two genotypes of melon (susceptible and resistant) were obtained by transcriptome analysis. Second, 391 transcription factors (TFs) were identified from the plant transcription factor database and cucurbit genomics database. Then, functional enrichment analysis indicated that these genes were mainly annotated in the process of transcription regulation. Third, 243 and 230 module-specific TFs were screened by weighted gene coexpression network analysis and short time series expression miner, respectively. Several TF genes, such as WRKYs and bHLHs, were regarded as key regulatory genes according to the values of significantly different modules. The coexpression network showed that these TF genes were significant correlated with resistance (R) genes, such as DRP2, RGA3, DRP1 and NB-ARC. Fourth, cis-acting element analysis illustrated that these R genes may bind to WRKY and bHLH. Finally, the expression of WRKY genes was verified by quantitative reverse transcription PCR (RT-qPCR). Phylogenetic analysis was carried out to further confirm that these TFs may play a critical role in Curcurbitaceae disease resistance. This study provides a new optimized combination strategy to explore the functions of TFs in a wide spectrum of biological processes. This strategy may also effectively predict potential relationships in the interactions of essential genes.

Coenzyme A-associated proteins (CAPs) are a category of functionally important proteins involved in multiple biological processes through interactions with coenzyme A (CoA). To date, unfortunately, the specific differences between CAPs and other proteins have yet to be systemically investigated. Moreover, there are no computational methods that can be used specifically to predict these proteins. Herein, we characterized CAPs from multifaceted viewpoints and revealed their specific preferences. Compared with other proteins, CAPs were more likely to possess binding regions for CoA and its derivatives, were evolutionarily highly conserved, exhibited ordered and hydrophobic structural conformations, and tended to be densely located in protein-protein interaction networks. Based on these biological insights, we built seven classifiers using predicted CoA-binding residue distributions, word embedding vectors, remote homolog numbers, evolutionary conservation, amino acid composition, predicted structural features and network properties. These classifiers could effectively identify CAPs in Homo sapiens, Mus musculus and Arabidopsis thaliana. The complementarity among the individual classifiers prompted us to build a two-layer stacking model named CAPE for improving prediction performance. We applied CAPE to identify some high-confidence candidates in the three species, which were tightly associated with the known functions of CAPs. Finally, we extended our algorithm to cross-species prediction, thereby developing a generic CAP prediction model. In summary, this work provides a comprehensive survey and an effective predictor for CAPs, which can help uncover the interplay between CoA and functionally relevant proteins.

Researchers have long been presented with the challenge imposed by the role of genetic heterogeneity in drug response. For many years, Pharmacogenomics and pharmacomicrobiomics has been investigating the influence of an individual's genetic background to drug response and disposition. More recently, the human gut microbiome has proven to play a crucial role in the way patients respond to different therapeutic drugs and it has been shown that by understanding the composition of the human microbiome, we can improve the drug efficacy and effectively identify drug targets. However, our knowledge on the effect of host genetics on specific gut microbes related to variation in drug metabolizing enzymes, the drug remains limited and therefore limits the application of joint host-microbiome genome-wide association studies. In this paper, we provide a historical overview of the complex interactions between the host, human microbiome and drugs. While discussing applications, challenges and opportunities of these studies, we draw attention to the critical need for inclusion of diverse populations and the development of an innovative and combined pharmacogenomics and pharmacomicrobiomics approach, that may provide an important basis in personalized medicine.

Single cell/nucleus RNA sequencing (scRNAseq) is emerging as an essential tool to unravel the phenotypic heterogeneity of cells in complex biological systems. While computational methods for scRNAseq cell type clustering have advanced, the ability to integrate datasets to identify common and novel cell types across experiments remains a challenge. Here, we introduce a cluster-to-cluster cell type matching method-FR-Match-that utilizes supervised feature selection for dimensionality reduction and incorporates shared information among cells to determine whether two cell type clusters share the same underlying multivariate gene expression distribution. FR-Match is benchmarked with existing cell-to-cell and cell-to-cluster cell type matching methods using both simulated and real scRNAseq data. FR-Match proved to be a stringent method that produced fewer erroneous matches of distinct cell subtypes and had the unique ability to identify novel cell phenotypes in new datasets. In silico validation demonstrated that the proposed workflow is the only self-contained algorithm that was robust to increasing numbers of true negatives (i.e. non-represented cell types). FR-Match was applied to two human brain scRNAseq datasets sampled from cortical layer 1 and full thickness middle temporal gyrus. When mapping cell types identified in specimens isolated from these overlapping human brain regions, FR-Match precisely recapitulated the laminar characteristics of matched cell type clusters, reflecting their distinct neuroanatomical distributions. An R package and Shiny application are provided at https://github.com/JCVenterInstitute/FRmatch for users to interactively explore and match scRNAseq cell type clusters with complementary visualization tools.

Deoxyribonucleic acid replication is one of the most crucial tasks taking place in the cell, and it has to be precisely regulated. This process is initiated in the replication origins (ORIs), and thus it is essential to identify such sites for a deeper understanding of the cellular processes and functions related to the regulation of gene expression. Considering the important tasks performed by ORIs, several experimental and computational approaches have been developed in the prediction of such sites. However, existing computational predictors for ORIs have certain curbs, such as building only single-feature encoding models, limited systematic feature engineering efforts and failure to validate model robustness. Hence, we developed a novel species-specific yeast predictor called yORIpred that accurately identify ORIs in the yeast genomes. To develop yORIpred, we first constructed optimal 40 baseline models by exploring eight different sequence-based encodings and five different machine learning classifiers. Subsequently, the predicted probability of 40 models was considered as the novel feature vector and carried out iterative feature learning approach independently using five different classifiers. Our systematic analysis revealed that the feature representation learned by the support vector machine algorithm (yORIpred) could well discriminate the distribution characteristics between ORIs and non-ORIs when compared with the other four algorithms. Comprehensive benchmarking experiments showed that yORIpred achieved superior and stable performance when compared with the existing predictors on the same training datasets. Furthermore, independent evaluation showcased the best and accurate performance of yORIpred thus underscoring the significance of iterative feature representation. To facilitate the users in obtaining their desired results without undergoing any mathematical, statistical or computational hassles, we developed a web server for the yORIpred predictor, which is available at: http://thegleelab.org/yORIpred.

Subcellular localization is a critical aspect of protein function and the potential application of proteins either as drugs or drug targets, or in industrial and domestic applications. However, the experimental determination of protein localization is time consuming and expensive. Therefore, various localization predictors have been developed for particular groups of species. Intriguingly, despite their major representation amongst biotechnological cell factories and pathogens, a meta-predictor based on sorting signals and specific for Gram-positive bacteria was still lacking. Here we present GP4, a protein subcellular localization meta-predictor mainly for Firmicutes, but also Actinobacteria, based on the combination of multiple tools, each specific for different sorting signals and compartments. Novelty elements include improved cell-wall protein prediction, including differentiation of the type of interaction, prediction of non-canonical secretion pathway target proteins, separate prediction of lipoproteins and better user experience in terms of parsability and interpretability of the results. GP4 aims at mimicking protein sorting as it would happen in a bacterial cell. As GP4 is not homology based, it has a broad applicability and does not depend on annotated databases with homologous proteins. Non-canonical usage may include little studied or novel species, synthetic and engineered organisms, and even re-use of the prediction data to develop custom prediction algorithms. Our benchmark analysis highlights the improved performance of GP4 compared to other widely used subcellular protein localization predictors. A webserver running GP4 is available at http://gp4.hpc.rug.nl/.

A promoter is a region in the DNA sequence that defines where the transcription of a gene by RNA polymerase initiates, which is typically located proximal to the transcription start site (TSS). How to correctly identify the gene TSS and the core promoter is essential for our understanding of the transcriptional regulation of genes. As a complement to conventional experimental methods, computational techniques with easy-to-use platforms as essential bioinformatics tools can be effectively applied to annotate the functions and physiological roles of promoters. In this work, we propose a deep learning-based method termed Depicter (Deep learning for predicting promoter), for identifying three specific types of promoters, i.e. promoter sequences with the TATA-box (TATA model), promoter sequences without the TATA-box (non-TATA model), and indistinguishable promoters (TATA and non-TATA model). Depicter is developed based on an up-to-date, species-specific dataset which includes Homo sapiens, Mus musculus, Drosophila melanogaster and Arabidopsis thaliana promoters. A convolutional neural network coupled with capsule layers is proposed to train and optimize the prediction model of Depicter. Extensive benchmarking and independent tests demonstrate that Depicter achieves an improved predictive performance compared with several state-of-the-art methods. The webserver of Depicter is implemented and freely accessible at https://depicter.erc.monash.edu/.

Beta-lactamases (BLs) are enzymes localized in the periplasmic space of bacterial pathogens, where they confer resistance to beta-lactam antibiotics. Experimental identification of BLs is costly yet crucial to understand beta-lactam resistance mechanisms. To address this issue, we present DeepBL, a deep learning-based approach by incorporating sequence-derived features to enable high-throughput prediction of BLs. Specifically, DeepBL is implemented based on the Small VGGNet architecture and the TensorFlow deep learning library. Furthermore, the performance of DeepBL models is investigated in relation to the sequence redundancy level and negative sample selection in the benchmark dataset. The models are trained on datasets of varying sequence redundancy thresholds, and the model performance is evaluated by extensive benchmarking tests. Using the optimized DeepBL model, we perform proteome-wide screening for all reviewed bacterium protein sequences available from the UniProt database. These results are freely accessible at the DeepBL webserver at http://deepbl.erc.monash.edu.au/.

NLRP3 inflammasome was introduced as a double-edged sword in tumorigenesis and influenced immunotherapy response by modulating host immunity. However, a systematic assessment of the NLRP3-inflammasome-related genes across human cancers is lacking, and the predictive role of NLRP3 inflammasome in cancer immunotherapy (CIT) response remains unexplored. Thus, in this study, we performed a pan-cancer analysis of NLRP3-inflammasome-related genes across 24 human cancers. Out of these 24 cancers, 15 cancers had significantly different expression of NLRP3-inflammasome-related genes between normal and tumor samples. Meanwhile, Cox regression analysis showed that the NLRP3 inflammasome score could be served as an independent prognostic factor in skin cutaneous melanoma. Further analysis indicated that NLRP3 inflammasome may influence tumor immunity mainly by mediating tumor-infiltrating lymphocytes and macrophages, and the effect of NLRP3 inflammasome on immunity is diverse across tumor types in tumor microenvironment. We also found that the NLRP3 inflammasome score could be a stronger predictor for immune signatures compared with tumor mutation burden (TMB) and glycolytic activity, which have been reported as immune predictors. Furthermore, analysis of the association between NLRP3 inflammasome and CIT response using six CIT response datasets revealed the predictive value of NLRP3 inflammasome for immunotherapy response of patients in diverse cancers. Our study illustrates the characterization of NLRP3 inflammasome in multiple cancer types and highlights its potential value as a predictive biomarker of CIT response, which can pave the way for further investigation of the prognostic and therapeutic potentials of NLRP3 inflammasome.

The power of genotype-phenotype association mapping studies increases greatly when contributions from multiple variants in a focal region are meaningfully aggregated. Currently, there are two popular categories of variant aggregation methods. Transcriptome-wide association studies (TWAS) represent a set of emerging methods that select variants based on their effect on gene expressions, providing pretrained linear combinations of variants for downstream association mapping. In contrast to this, kernel methods such as sequence kernel association test (SKAT) model genotypic and phenotypic variance use various kernel functions that capture genetic similarity between subjects, allowing nonlinear effects to be included. From the perspective of machine learning, these two methods cover two complementary aspects of feature engineering: feature selection/pruning and feature aggregation. Thus far, no thorough comparison has been made between these categories, and no methods exist which incorporate the advantages of TWAS- and kernel-based methods. In this work, we developed a novel method called kernel-based TWAS (kTWAS) that applies TWAS-like feature selection to a SKAT-like kernel association test, combining the strengths of both approaches. Through extensive simulations, we demonstrate that kTWAS has higher power than TWAS and multiple SKAT-based protocols, and we identify novel disease-associated genes in Wellcome Trust Case Control Consortium genotyping array data and MSSNG (Autism) sequence data. The source code for kTWAS and our simulations are available in our GitHub repository (https://github.com/theLongLab/kTWAS).

Several studies to date have proposed different types of interpreters for measuring the degree of pathogenicity of variants. However, in predicting the disease type and disease-gene associations, scholars face two essential challenges, namely the vast number of existing variants and the existence of variants which are recognized as variant of uncertain significance (VUS). To tackle these challenges, we propose algorithms to assign a significance to each gene rather than each variant, describing its degree of pathogenicity. Since the interpreters identified most of the variants as VUS, most of the gene scores were identified as uncertain significance. To predict the uncertain significance scores, we design two matrix factorization-based models: the common latent space model uses genomics variant data as well as heterogeneous clinical data, while the single-matrix factorization model can be used when heterogeneous clinical data are unavailable. We have managed to show that the models successfully predict the uncertain significance scores with low error and high accuracy. Moreover, to evaluate the effectiveness of our novel input features, we train five different multi-label classifiers including a feedforward neural network with the same feature set and show they all achieve high accuracy as the main impact of our approach comes from the features. Availability: The source code is freely available at https://github.com/sabdollahi/CoLaSpSMFM.

MOTIVATION: N7-methylguanosine (m7G) is an important epigenetic modification, playing an essential role in gene expression regulation. Therefore, accurate identification of m7G modifications will facilitate revealing and in-depth understanding their potential functional mechanisms. Although high-throughput experimental methods are capable of precisely locating m7G sites, they are still cost ineffective. Therefore, it's necessary to develop new methods to identify m7G sites. RESULTS: In this work, by using the iterative feature representation algorithm, we developed a machine learning based method, namely m7G-IFL, to identify m7G sites. To demonstrate its superiority, m7G-IFL was evaluated and compared with existing predictors. The results demonstrate that our predictor outperforms existing predictors in terms of accuracy for identifying m7G sites. By analyzing and comparing the features used in the predictors, we found that the positive and negative samples in our feature space were more separated than in existing feature space. This result demonstrates that our features extracted more discriminative information via the iterative feature learning process, and thus contributed to the predictive performance improvement.

Almost all currently approved systemic therapies for hepatocellular carcinoma (HCC) failed to achieve satisfactory therapeutic effect. Exploring tailored treatment strategies for different individuals provides an approach with the potential to maximize clinical benefit. Previously, multiple studies have reported that hepatoma cell lines belonging to different molecular subtypes respond differently to the same treatment. However, these studies only focused on a small number of typical chemotherapy or targeted drugs across limited cell lines due to time and cost constraints. To compensate for the deficiency of previous experimental researches as well as link molecular classification with therapeutic response, we conducted a comprehensive in silico screening, comprising nearly 2000 compounds, to identify compounds with subclass-specific efficacy. Here, we first identified two transcriptome-based HCC subclasses (AS1 and AS2) and then made comparison of drug response between two subclasses. As a result, we not only found that some agents previously considered to have low efficacy in HCC treatment might have promising therapeutic effects for certain subclass, but also identified novel therapeutic compounds that were not routinely used as anti-tumor drugs in clinic. Discovery of agents with subclass-specific efficacy has potential in changing the status quo of population-based therapies in HCC and providing new insights into precision oncology.

It is of considerable interest to detect somatic mutations in paired tumor and normal sequencing data. A number of callers that are based on statistical or machine learning approaches have been developed to detect somatic small variants. However, they take into consideration only limited information about the reference and potential variant allele in both tumor and normal samples at a candidate somatic site. Also, they differ in how biological and technological noises are addressed. Hence, they are expected to produce divergent outputs. To overcome the drawbacks of existing somatic callers, we develop a deep learning-based tool called DeepSSV, which employs a convolutional neural network (CNN) model to learn increasingly abstract feature representations from the raw data in higher feature layers. DeepSSV creates a spatially oriented representation of read alignments around the candidate somatic sites adapted for the convolutional architecture, which enables it to expand to effectively gather scattered evidence. Moreover, DeepSSV incorporates the mapping information of both reference allele-supporting and variant allele-supporting reads in the tumor and normal samples at a genomic site that are readily available in the pileup format file. Together, the CNN model can process the whole alignment information. Such representational richness allows the model to capture the dependencies in the sequence and identify context-based sequencing artifacts. We fitted the model on ground truth somatic mutations and did benchmarking experiments on simulated and real tumors. The benchmarking results demonstrate that DeepSSV outperforms its state-of-the-art competitors in overall F1 score.

Origins of replication sites (ORIs), which refers to the initiative locations of genomic DNA replication, play essential roles in DNA replication process. Detection of ORIs' distribution in genome scale is one of key steps to in-depth understanding their regulation mechanisms. In this study, we presented a novel machine learning-based approach called Stack-ORI encompassing 10 cell-specific prediction models for identifying ORIs from four different eukaryotic species (Homo sapiens, Mus musculus, Drosophila melanogaster and Arabidopsis thaliana). For each cell-specific model, we employed 12 feature encoding schemes that cover nucleic acid composition, position-specific and physicochemical properties information. The optimal feature set was identified from each encoding individually and developed their respective baseline models using the eXtreme Gradient Boosting (XGBoost) classifier. Subsequently, the predicted scores of 12 baseline models are integrated as a novel feature vector to train XGBoost and develop the final model. Extensive experimental results show that Stack-ORI achieves significantly better performance as compared with their baseline models on both training and independent datasets. Interestingly, Stack-ORI consistently outperforms existing predictor in all cell-specific models, not only on training but also on independent test. Moreover, our novel approach provides necessary interpretations that help understanding model success by leveraging the powerful SHapley Additive exPlanation algorithm, thus underlining the most important feature encoding schemes significant for predicting cell-specific ORIs.

Drug similarities play an important role in modern biology and medicine, as they help scientists gain deep insights into drugs' therapeutic mechanisms and conduct wet labs that may significantly improve the efficiency of drug research and development. Nowadays, a number of drug-related databases have been constructed, with which many methods have been developed for computing similarities between drugs for studying associations between drugs, human diseases, proteins (drug targets) and more. In this review, firstly, we briefly introduce the publicly available drug-related databases. Secondly, based on different drug features, interaction relationships and multimodal data, we summarize similarity calculation methods in details. Then, we discuss the applications of drug similarities in various biological and medical areas. Finally, we evaluate drug similarity calculation methods with common evaluation metrics to illustrate the important roles of drug similarity measures on different applications.

With the development of high-throughput technology and the accumulation of biomedical data, the prior information of biological entity can be calculated from different aspects. Specifically, drug-drug similarities can be measured from target profiles, drug-drug interaction and side effects. Similarly, different methods and data sources to calculate disease ontology can result in multiple measures of pairwise disease similarities. Therefore, in computational drug repositioning, developing a dynamic method to optimize the fusion process of multiple similarities is a crucial and challenging task. In this study, we propose a multi-similarities bilinear matrix factorization (MSBMF) method to predict promising drug-associated indications for existing and novel drugs. Instead of fusing multiple similarities into a single similarity matrix, we concatenate these similarity matrices of drug and disease, respectively. Applying matrix factorization methods, we decompose the drug-disease association matrix into a drug-feature matrix and a disease-feature matrix. At the same time, using these feature matrices as basis, we extract effective latent features representing the drug and disease similarity matrices to infer missing drug-disease associations. Moreover, these two factored matrices are constrained by non-negative factorization to ensure that the completed drug-disease association matrix is biologically interpretable. In addition, we numerically solve the MSBMF model by an efficient alternating direction method of multipliers algorithm. The computational experiment results show that MSBMF obtains higher prediction accuracy than the state-of-the-art drug repositioning methods in cross-validation experiments. Case studies also demonstrate the effectiveness of our proposed method in practical applications. Availability: The data and code of MSBMF are freely available at https://github.com/BioinformaticsCSU/MSBMF. Corresponding author: Jianxin Wang, School of Computer Science and Engineering, Central South University, Changsha, Hunan 410083, P. R. China. E-mail: jxwang@mail.csu.edu.cn Supplementary Data: Supplementary data are available online at https://academic.oup.com/bib.

Effective drug discovery contributes to the treatment of numerous diseases but is limited by high costs and long cycles. The Quantitative Structure-Activity Relationship (QSAR) method was introduced to evaluate the activity of a large number of compounds virtually, reducing the time and labor costs required for chemical synthesis and experimental determination. Hence, this method increases the efficiency of drug discovery. To meet the needs of researchers to utilize this technology, numerous QSAR-related web servers, such as Web-4D-QSAR and DPubChem, have been developed in recent years. However, none of the servers mentioned above can perform a complete QSAR modeling and supply activity prediction functions. We introduce Cloud 3D-QSAR by integrating the functions of molecular structure generation, alignment, molecular interaction field (MIF) computing and results analysis to provide a one-stop solution. We rigidly validated this server, and the activity prediction correlation was R2 = 0.934 in 834 test molecules. The sensitivity, specificity and accuracy were 86.9%, 94.5% and 91.5%, respectively, with AUC = 0.981, AUCPR = 0.971. The Cloud 3D-QSAR server may facilitate the development of good QSAR models in drug discovery. Our server is free and now available at http://chemyang.ccnu.edu.cn/ccb/server/cloud3dQSAR/ and http://agroda.gzu.edu.cn:9999/ccb/server/cloud3dQSAR/.

Breast cancer is a highly heterogeneous disease, and there are many forms of categorization for breast cancer based on gene expression profiles. Gene expression profiles are variables and may show differences if measured at different time points or under different conditions. In contrast, biological networks are relatively stable over time and under different conditions. In this study, we used a gene interaction network from a new point of view to explore the subtypes of breast cancer based on individual-specific edge perturbations measured by relative gene expression value. Our study reveals that there are four breast cancer subtypes based on gene interaction perturbations at the individual level. The new network-based subtypes of breast cancer show strong heterogeneity in prognosis, somatic mutations, phenotypic changes and enriched pathways. The network-based subtypes are closely related to the PAM50 subtypes and immunohistochemistry index. This work helps us to better understand the heterogeneity and mechanisms of breast cancer from a network perspective.

An interaction between pharmacological agents can trigger unexpected adverse events. Capturing richer and more comprehensive information about drug-drug interactions (DDIs) is one of the key tasks in public health and drug development. Recently, several knowledge graph (KG) embedding approaches have received increasing attention in the DDI domain due to their capability of projecting drugs and interactions into a low-dimensional feature space for predicting links and classifying triplets. However, existing methods only apply a uniformly random mode to construct negative samples. As a consequence, these samples are often too simplistic to train an effective model. In this paper, we propose a new KG embedding framework by introducing adversarial autoencoders (AAEs) based on Wasserstein distances and Gumbel-Softmax relaxation for DDI tasks. In our framework, the autoencoder is employed to generate high-quality negative samples and the hidden vector of the autoencoder is regarded as a plausible drug candidate. Afterwards, the discriminator learns the embeddings of drugs and interactions based on both positive and negative triplets. Meanwhile, in order to solve vanishing gradient problems on the discrete representation-an inherent flaw in traditional generative models-we utilize the Gumbel-Softmax relaxation and the Wasserstein distance to train the embedding model steadily. We empirically evaluate our method on two tasks: link prediction and DDI classification. The experimental results show that our framework can attain significant improvements and noticeably outperform competitive baselines. Supplementary information: Supplementary data and code are available at https://github.com/dyf0631/AAE_FOR_KG.

Over the last decade, genome-wide association studies (GWAS) have discovered thousands of genetic variants underlying complex human diseases and agriculturally important traits. These findings have been utilized to dissect the biological basis of diseases, to develop new drugs, to advance precision medicine and to boost breeding. However, the potential of GWAS is still underexploited due to methodological limitations. Many challenges have emerged, including detecting epistasis and single-nucleotide polymorphisms (SNPs) with small effects and distinguishing causal variants from other SNPs associated through linkage disequilibrium. These issues have motivated advancements in GWAS analyses in two contrasting cultures-statistical modelling and machine learning. In this review, we systematically present the basic concepts and the benefits and limitations in both methods. We further discuss recent efforts to mitigate their weaknesses. Additionally, we summarize the state-of-the-art tools for detecting the missed signals, ultrarare mutations and gene-gene interactions and for prioritizing SNPs. Our work can offer both theoretical and practical guidelines for performing GWAS analyses and for developing further new robust methods to fully exploit the potential of GWAS.

Exploring protein-ligand interactions is a subject of immense interest, as it provides deeper insights into molecular recognition, mechanism of interaction and subsequent functions. Predicting an accurate model for a protein-ligand interaction is a challenging task. Molecular docking is a computational method used for predicting the preferred orientation, binding conformations and the binding affinity of a ligand to a macromolecular target, especially protein. It has been applied in 'virtual high-throughput screening' of chemical libraries containing millions of compounds to find potential leads in drug design and discovery. Here, we have developed InstaDock, a free and open access Graphical User Interface (GUI) program that performs molecular docking and high-throughput virtual screening efficiently. InstaDock is a single-click GUI that uses QuickVina-W, a modified version of AutoDock Vina for docking calculations, made especially for the convenience of non-bioinformaticians and for people who are not experts in using computers. InstaDock facilitates onboard analysis of docking and visual results in just a single click. To sum up, InstaDock is the easiest and more interactive interface than ever existing GUIs for molecular docking and high-throughput virtual screening. InstaDock is freely available for academic and industrial research purposes via https://hassanlab.org/instadock.

BACKGROUND: Determining drug-disease associations is an integral part in the process of drug development. However, the identification of drug-disease associations through wet experiments is costly and inefficient. Hence, the development of efficient and high-accuracy computational methods for predicting drug-disease associations is of great significance. RESULTS: In this paper, we propose a novel computational method named as layer attention graph convolutional network (LAGCN) for the drug-disease association prediction. Specifically, LAGCN first integrates the known drug-disease associations, drug-drug similarities and disease-disease similarities into a heterogeneous network, and applies the graph convolution operation to the network to learn the embeddings of drugs and diseases. Second, LAGCN combines the embeddings from multiple graph convolution layers using an attention mechanism. Third, the unobserved drug-disease associations are scored based on the integrated embeddings. Evaluated by 5-fold cross-validations, LAGCN achieves an area under the precision-recall curve of 0.3168 and an area under the receiver-operating characteristic curve of 0.8750, which are better than the results of existing state-of-the-art prediction methods and baseline methods. The case study shows that LAGCN can discover novel associations that are not curated in our dataset. CONCLUSION: LAGCN is a useful tool for predicting drug-disease associations. This study reveals that embeddings from different convolution layers can reflect the proximities of different orders, and combining the embeddings by the attention mechanism can improve the prediction performances.

Mechanistic computational models enable the study of regulatory mechanisms implicated in various biological processes. These models provide a means to analyze the dynamics of the systems they describe, and to study and interrogate their properties, and provide insights about the emerging behavior of the system in the presence of single or combined perturbations. Aimed at those who are new to computational modeling, we present here a practical hands-on protocol breaking down the process of mechanistic modeling of biological systems in a succession of precise steps. The protocol provides a framework that includes defining the model scope, choosing validation criteria, selecting the appropriate modeling approach, constructing a model and simulating the model. To ensure broad accessibility of the protocol, we use a logical modeling framework, which presents a lower mathematical barrier of entry, and two easy-to-use and popular modeling software tools: Cell Collective and GINsim. The complete modeling workflow is applied to a well-studied and familiar biological process-the lac operon regulatory system. The protocol can be completed by users with little to no prior computational modeling experience approximately within 3 h.

Cholangiocarcinoma (CCA) is a type of cancer with limited treatment options and a poor prognosis. Although some important genes and pathways associated with CCA have been identified, the relationship between coexpression and phenotype in CCA at the systems level remains unclear. In this study, the relationships underlying the molecular and clinical characteristics of CCA were investigated by employing weighted gene coexpression network analysis (WGCNA). The gene expression profiles and clinical features of 36 patients with CCA were analyzed to identify differentially expressed genes (DEGs). Subsequently, the coexpression of DEGs was determined by using the WGCNA method to investigate the correlations between pairs of genes. Network modules that were significantly correlated with clinical traits were identified. In total, 1478 mRNAs were found to be aberrantly expressed in CCA. Seven coexpression modules that significantly correlated with clinical characteristics were identified and assigned representative colors. Among the 7 modules, the green and blue modules were significantly related to tumor differentiation. Seventy-eight hub genes that were correlated with tumor differentiation were found in the green and blue modules. Survival analysis showed that 17 hub genes were prognostic biomarkers for CCA patients. In addition, we found five new targets (ISM1, SULT1B1, KIFC1, AURKB and CCNB1) that have not been studied in the context of CCA and verified their differential expression in CCA through experiments. Our results not only promote our understanding of the relationship between the transcriptome and clinical data in CCA but will also guide the development of targeted molecular therapy for CCA.

Ontologies have long been employed in the life sciences to formally represent and reason over domain knowledge and they are employed in almost every major biological database. Recently, ontologies are increasingly being used to provide background knowledge in similarity-based analysis and machine learning models. The methods employed to combine ontologies and machine learning are still novel and actively being developed. We provide an overview over the methods that use ontologies to compute similarity and incorporate them in machine learning methods; in particular, we outline how semantic similarity measures and ontology embeddings can exploit the background knowledge in ontologies and how ontologies can provide constraints that improve machine learning models. The methods and experiments we describe are available as a set of executable notebooks, and we also provide a set of slides and additional resources at https://github.com/bio-ontology-research-group/machine-learning-with-ontologies.

Long noncoding RNAs (lncRNAs) play significant roles in various physiological and pathological processes via their interactions with biomolecules like DNA, RNA and protein. The existing in silico methods used for predicting the functions of lncRNA mainly rely on calculating the similarity of lncRNA or investigating whether an lncRNA can interact with a specific biomolecule or disease. In this work, we explored the functions of lncRNA from a different perspective: we presented a tool for predicting the interaction biomolecule type for a given lncRNA. For this purpose, we first investigated the main molecular mechanisms of the interactions of lncRNA-RNA, lncRNA-protein and lncRNA-DNA. Then, we developed an ensemble deep learning model: lncIBTP (lncRNA Interaction Biomolecule Type Prediction). This model predicted the interactions between lncRNA and different types of biomolecules. On the 5-fold cross-validation, the lncIBTP achieves average values of 0.7042 in accuracy, 0.7903 and 0.6421 in macro-average area under receiver operating characteristic curve and precision-recall curve, respectively, which illustrates the model effectiveness. Besides, based on the analysis of the collected published data and prediction results, we hypothesized that the characteristics of lncRNAs that interacted with DNA may be different from those that interacted with only RNA.

N6-methyladenosine (m6A) modification can regulate a variety of biological processes. However, the implications of m6A modification in lung adenocarcinoma (LUAD) remain largely unknown. Here, we systematically evaluated the m6A modification features in more than 2400 LUAD samples by analyzing the multi-omics features of 23 m6A regulators. We depicted the genetic variation features of m6A regulators, and found mutations of FTO and YTHDF3 were linked to worse overall survival. Many m6A regulators were aberrantly expressed in tumors, among which FTO, IGF2BP3, YTHDF1 and RBM15 showed consistent alteration features across 11 independent cohorts. Besides, the regulator-pathway interaction network demonstrated that m6A modification was associated with various biological pathways, including immune-related pathways. The correlation between m6A regulators and tumor microenvironment was also assessed. We found that LRPPRC was negatively correlated with most tumor-infiltrating immune cells. On the other hand, we established a scoring tool named m6Sig, which was positively correlated with PD-L1 expression and could reflect both the tumor microenvironment characterization and prognosis of LUAD patients. Comparison of CNV between high and low m6Sig groups revealed differences on chromosome 7. Application of m6Sig on an anti-PD-L1 immunotherapy cohort confirmed that the high m6Sig group demonstrated therapeutic advantages and clinical benefits. Our study indicated that m6A modification is involved in many aspects of LUAD and contributes to tumor microenvironment formation. A better understanding of m6A modification will provide more insights into the molecular mechanisms of LUAD and facilitate developing more effective personalized treatment strategies. A web application was built along with this study (http://www.bioinfo-zs.com/luadexpress/).

Comment in Brief Bioinform. 2022 Jan 17;23(1):

Using gene-regulatory-networks-based approach for single-cell expression profiles can reveal unprecedented details about the effects of external and internal factors. However, noise and batch effect in sparse single-cell expression profiles can hamper correct estimation of dependencies among genes and regulatory changes. Here, we devise a conceptually different method using graphwavelet filters for improving gene network (GWNet)-based analysis of the transcriptome. Our approach improved the performance of several gene network-inference methods. Most Importantly, GWNet improved consistency in the prediction of gene regulatory network using single-cell transcriptome even in the presence of batch effect. The consistency of predicted gene network enabled reliable estimates of changes in the influence of genes not highlighted by differential-expression analysis. Applying GWNet on the single-cell transcriptome profile of lung cells, revealed biologically relevant changes in the influence of pathways and master regulators due to ageing. Surprisingly, the regulatory influence of ageing on pneumocytes type II cells showed noticeable similarity with patterns due to the effect of novel coronavirus infection in human lung.

Short read whole genome sequencing has become widely used to detect structural variants in human genetic studies and clinical practices. However, accurate detection of structural variants is a challenging task. Especially existing structural variant detection approaches produce a large proportion of incorrect calls, so effective structural variant filtering approaches are urgently needed. In this study, we propose a novel deep learning-based approach, DeepSVFilter, for filtering structural variants in short read whole genome sequencing data. DeepSVFilter encodes structural variant signals in the read alignments as images and adopts the transfer learning with pre-trained convolutional neural networks as the classification models, which are trained on the well-characterized samples with known high confidence structural variants. We use two well-characterized samples to demonstrate DeepSVFilter's performance and its filtering effect coupled with commonly used structural variant detection approaches. The software DeepSVFilter is implemented using Python and freely available from the website at https://github.com/yongzhuang/DeepSVFilter.

Data from the SEER reports reveal that the occurrence rate of a cancer type generally follows a unimodal distribution over age, peaking at an age that is cancer-type specific and ranges from 30+ through 70+. Previous studies attribute such bell-shaped distributions to the reduced proliferative potential in senior years but fail to explain why some cancers have their occurrence peak at 30+ or 40+. We present a computational model to offer a new explanation to such distributions. The model uses two factors to explain the observed age-dependent cancer occurrence rates: cancer risk of an organ and the availability level of the growth signals in circulation needed by a cancer type, with the former increasing and the latter decreasing with age. Regression analyses were conducted of known occurrence rates against such factors for triple negative breast cancer, testicular cancer and cervical cancer; and all achieved highly tight fitting results, which were also consistent with clinical, gene-expression and cancer-drug data. These reveal a fundamentally important relationship: while cancer is driven by endogenous stressors, it requires sufficient levels of exogenous growth signals to happen, hence suggesting the realistic possibility for treating cancer via cleaning out the growth signals in circulation needed by a cancer.

Non-coding RNAs (ncRNAs) play crucial roles in multiple biological processes. However, only a few ncRNAs' functions have been well studied. Given the significance of ncRNAs classification for understanding ncRNAs' functions, more and more computational methods have been introduced to improve the classification automatically and accurately. In this paper, based on a convolutional neural network and a deep forest algorithm, multi-grained cascade forest (GcForest), we propose a novel deep fusion learning framework, GcForest fusion method (GCFM), to classify alignments of ncRNA sequences for accurate clustering of ncRNAs. GCFM integrates a multi-view structure feature representation including sequence-structure alignment encoding, structure image representation and shape alignment encoding of structural subunits, enabling us to capture the potential specificity between ncRNAs. For the classification of pairwise alignment of two ncRNA sequences, the F-value of GCFM improves 6% than an existing alignment-based method. Furthermore, the clustering of ncRNA families is carried out based on the classification matrix generated from GCFM. Results suggest better performance (with 20% accuracy improved) than existing ncRNA clustering methods (RNAclust, Ensembleclust and CNNclust). Additionally, we apply GCFM to construct a phylogenetic tree of ncRNA and predict the probability of interactions between RNAs. Most ncRNAs are located correctly in the phylogenetic tree, and the prediction accuracy of RNA interaction is 90.63%. A web server (http://bmbl.sdstate.edu/gcfm/) is developed to maximize its availability, and the source code and related data are available at the same URL.

Current variant calling (VC) approaches have been designed to leverage populations of long-range haplotypes and were benchmarked using populations of European descent, whereas most genetic diversity is found in non-European such as Africa populations. Working with these genetically diverse populations, VC tools may produce false positive and false negative results, which may produce misleading conclusions in prioritization of mutations, clinical relevancy and actionability of genes. The most prominent question is which tool or pipeline has a high rate of sensitivity and precision when analysing African data with either low or high sequence coverage, given the high genetic diversity and heterogeneity of this data. Here, a total of 100 synthetic Whole Genome Sequencing (WGS) samples, mimicking the genetics profile of African and European subjects for different specific coverage levels (high/low), have been generated to assess the performance of nine different VC tools on these contrasting datasets. The performances of these tools were assessed in false positive and false negative call rates by comparing the simulated golden variants to the variants identified by each VC tool. Combining our results on sensitivity and positive predictive value (PPV), VarDict [PPV = 0.999 and Matthews correlation coefficient (MCC) = 0.832] and BCFtools (PPV = 0.999 and MCC = 0.813) perform best when using African population data on high and low coverage data. Overall, current VC tools produce high false positive and false negative rates when analysing African compared with European data. This highlights the need for development of VC approaches with high sensitivity and precision tailored for populations characterized by high genetic variations and low linkage disequilibrium.

Biomedical knowledge graphs (KGs), which can help with the understanding of complex biological systems and pathologies, have begun to play a critical role in medical practice and research. However, challenges remain in their embedding and use due to their complex nature and the specific demands of their construction. Existing studies often suffer from problems such as sparse and noisy datasets, insufficient modeling methods and non-uniform evaluation metrics. In this work, we established a comprehensive KG system for the biomedical field in an attempt to bridge the gap. Here, we introduced PharmKG, a multi-relational, attributed biomedical KG, composed of more than 500 000 individual interconnections between genes, drugs and diseases, with 29 relation types over a vocabulary of ~8000 disambiguated entities. Each entity in PharmKG is attached with heterogeneous, domain-specific information obtained from multi-omics data, i.e. gene expression, chemical structure and disease word embedding, while preserving the semantic and biomedical features. For baselines, we offered nine state-of-the-art KG embedding (KGE) approaches and a new biological, intuitive, graph neural network-based KGE method that uses a combination of both global network structure and heterogeneous domain features. Based on the proposed benchmark, we conducted extensive experiments to assess these KGE models using multiple evaluation metrics. Finally, we discussed our observations across various downstream biological tasks and provide insights and guidelines for how to use a KG in biomedicine. We hope that the unprecedented quality and diversity of PharmKG will lead to advances in biomedical KG construction, embedding and application.

African swine fever virus (ASFV) poses serious threats to the pig industry. The multigene family (MGF) proteins are extensively distributed in ASFVs and are generally classified into five families, including MGF-100, MGF-110, MGF-300, MGF-360 and MGF-505. Most MGF proteins, however, have not been well characterized and classified within each family. To bridge this gap, this study first classified MGF proteins into 31 groups based on protein sequence homology and network clustering. A web server for classifying MGF proteins was established and kept available for free at http://www.computationalbiology.cn/MGF/home.html. Results showed that MGF groups of the same family were most similar to each other and had conserved sequence motifs; the genetic diversity of MGF groups varied widely, mainly due to the occurrence of indels. In addition, the MGF proteins were predicted to have large structural and functional diversity, and MGF proteins of the same MGF family tended to have similar structure, location and function. Reconstruction of the ancestral states of MGF groups along the ASFV phylogeny showed that most MGF groups experienced either the copy number variations or the gain-or-loss changes, and most of these changes happened within strains of the same genotype. It is found that the copy number decrease and the loss of MGF groups were much larger than the copy number increase and the gain of MGF groups, respectively, suggesting the ASFV tended to lose MGF proteins in the evolution. Overall, the work provides a detailed classification for MGF proteins and would facilitate further research on MGF proteins.

Drugs are the imperial part of modern society, but along with their therapeutic effects, drugs can also cause adverse effects, which can be mild to morbid. Pharmacovigilance is the process of collection, detection, assessment, monitoring and prevention of adverse drug events in both clinical trials as well as in the post-marketing phase. The recent trends in increasing unknown adverse events, known as signals, have raised the need to develop an ideal system for monitoring and detecting the potential signals timely. The process of signal management comprises of techniques to identify individual case safety reports systematically. Automated signal detection is highly based upon the data mining of the spontaneous reporting system such as reports from health care professional, observational studies, medical literature or from social media. If a signal is not managed properly, it can become an identical risk associated with the drug which can be hazardous for the patient safety and may have fatal outcomes which may impact health care system adversely. Once a signal is detected quantitatively, it can be further processed by the signal management team for the qualitative analysis and further evaluations. The main components of automated signal detection are data extraction, data acquisition, data selection, and data analysis and data evaluation. This system must be developed in the correct format and context, which eventually emphasizes the quality of data collected and leads to the optimal decision-making based upon the scientific evaluation.

The cell-free DNA (cfDNA) methylation profile in liquid biopsy has been utilized to diagnose early-stage disease and estimate therapy response. However, typical clinical procedures are capable of purifying only very small amounts of cfDNA. Whole-genome bisulfite sequencing (WGBS) is the gold standard for measuring DNA methylation; however, WGBS using small amounts of fragmented DNA introduces a critical challenge for data analysis, namely a low-mapping ratio. The resulting low sequencing depth and low coverage of CpG sites genome-wide is a bottleneck for the clinical application of cfDNA-based WGBS assays. We developed LiBis (Low-input Bisulfite Sequencing), a novel method for low-input WGBS data alignment. By dynamically clipping initially unmapped reads and remapping clipped fragments, we judiciously rescued those reads and uniquely aligned them to the genome. By substantially increasing the mapping ratio by up to 88%, LiBis dramatically improved the number of informative CpGs and the precision in quantifying the methylation status of individual CpG sites. LiBis significantly improved the cost efficiency of low-input WGBS experiments by dynamically removing contamination introduced by random priming. The high sensitivity and cost effectiveness afforded by LiBis for low-input samples will allow the discovery of genetic and epigenetic features suitable for downstream analysis and biomarker identification using liquid biopsy.

Structures of genetic regulatory networks are not fixed. These structural perturbations can cause changes to the reachability of systems' state spaces. As system structures are related to genotypes and state spaces are related to phenotypes, it is important to study the relationship between structures and state spaces. However, there is still no method can quantitively describe the reachability differences of two state spaces caused by structural perturbations. Therefore, Difference in Reachability between State Spaces (DReSS) is proposed. DReSS index family can quantitively describe differences of reachability, attractor sets between two state spaces and can help find the key structure in a system, which may influence system's state space significantly. First, basic properties of DReSS including non-negativity, symmetry and subadditivity are proved. Then, typical examples are shown to explain the meaning of DReSS and the differences between DReSS and traditional graph distance. Finally, differences of DReSS distribution between real biological regulatory networks and random networks are compared. Results show most structural perturbations in biological networks tend to affect reachability inside and between attractor basins rather than to affect attractor set itself when compared with random networks, which illustrates that most genotype differences tend to influence the proportion of different phenotypes and only a few ones can create new phenotypes. DReSS can provide researchers with a new insight to study the relation between genotypes and phenotypes.

At present, computational methods for drug repositioning are mainly based on the whole structures of drugs, which limits the discovery of new functions due to the similarities between local structures of drugs. In this article, we, for the first time, integrated the features of chemical-genomics (substructure-domain) and pharmaco-genomics (domain-indication) based on the assumption that drug-target interactions are mediated by the substructures of drugs and the domains of proteins to identify the relationships between substructure-indication and establish a drug-substructure-indication network for predicting all therapeutic effects of tested drugs through only information on the substructures of drugs. In total, 83 205 drug-indication relationships with different correlation scores were obtained. We used three different verification methods to indicate the accuracy of the method and the reliability of the scoring system. We predicted all indications of olaparib using our method, including the known antitumor effect and unknown antiviral effect verified by literature, and we also discovered the inhibitory mechanism of olaparib toward DNA repair through its specific sub494 (o = C-C: C), as it participates in the low synthesis of the poly subfunction of the apoptosis pathway (hsa04210) by inhibiting the Inositol 1,4,5-trisphosphate receptor(s) (ITPRs) and hydrolyzing poly (ADP ribose) polymerases. ElectroCardioGrams of four drugs (quinidine, amiodarone, milrinone and fosinopril) demonstrated the effect of anti-arrhythmia. Unlike previous studies focusing on the overall structures of drugs, our research has great potential in the search for more therapeutic effects of drugs and in predicting all potential effects and mechanisms of a drug from the local structural similarity.

Although a wide variety of machine learning (ML) algorithms have been utilized to learn quantitative structure-activity relationships (QSARs), there is no agreed single best algorithm for QSAR learning. Therefore, a comprehensive understanding of the performance characteristics of popular ML algorithms used in QSAR learning is highly desirable. In this study, five linear algorithms [linear function Gaussian process regression (linear-GPR), linear function support vector machine (linear-SVM), partial least squares regression (PLSR), multiple linear regression (MLR) and principal component regression (PCR)], three analogizers [radial basis function support vector machine (rbf-SVM), K-nearest neighbor (KNN) and radial basis function Gaussian process regression (rbf-GPR)], six symbolists [extreme gradient boosting (XGBoost), Cubist, random forest (RF), multiple adaptive regression splines (MARS), gradient boosting machine (GBM), and classification and regression tree (CART)] and two connectionists [principal component analysis artificial neural network (pca-ANN) and deep neural network (DNN)] were employed to learn the regression-based QSAR models for 14 public data sets comprising nine physicochemical properties and five toxicity endpoints. The results show that rbf-SVM, rbf-GPR, XGBoost and DNN generally illustrate better performances than the other algorithms. The overall performances of different algorithms can be ranked from the best to the worst as follows: rbf-SVM > XGBoost > rbf-GPR > Cubist > GBM > DNN > RF > pca-ANN > MARS > linear-GPR ≈ KNN > linear-SVM ≈ PLSR > CART ≈ PCR ≈ MLR. In terms of prediction accuracy and computational efficiency, SVM and XGBoost are recommended to the regression learning for small data sets, and XGBoost is an excellent choice for large data sets. We then investigated the performances of the ensemble models by integrating the predictions of multiple ML algorithms. The results illustrate that the ensembles of two or three algorithms in different categories can indeed improve the predictions of the best individual ML algorithms.

Transcriptomic deregulation by epigenetic mechanisms plays a crucial role in the heterogeneous progression of colorectal cancer (CRC). Herein, we first demonstrated that the frequencies of the aberrancies of DNA methylation-correlated (METcor) and microRNA (miRNA)-correlated (MIRcor) genes were significantly co-regulated. Next, through integrative clustering of the expression profiles of METcor and MIRcor genes, four molecular subtypes were identified in CRC patients from The Cancer Genome Atlas and then validated in four independent datasets. More importantly, the four subtypes were well characterized and showed distinct clinical and molecular features: (i) S-I: high metabolic activity, sensitive to 5-fluorouracil-based chemotherapy and good prognosis; (ii) S-II: moderate metabolic activity, marked proliferation, frequent KRAS mutation and intermediate prognosis; (iii) S-III: moderate metabolic activity, marked proliferation, promoter DNA hypermethylation, high mutation burden, frequent BRAF and EGFR mutations, moderate levels of epithelial-mesenchymal transition (EMT) and transforming growth factor β (TGFβ) signals, immune-inflamed phenotype, sensitive to cetuximab and death protein-1 inhibitor treatment and relatively poor prognosis and (iv) S-IV: miRNA overexpression, stem/serrated/mesenchymal-like properties, hypoxia, high levels of EMT and TGFβ signals, immune-excluded phenotype and poor prognosis. Overall, this study established a molecular classification based on epigenetically regulated gene expression profiles, thereby providing a better understanding of the epigenetic mechanisms underlying CRC heterogeneity.

The identification of rare haplotypes may greatly expand our knowledge in the genetic architecture of both complex and monogenic traits. To this aim, we developed PERHAPS (Paired-End short Reads-based HAPlotyping from next-generation Sequencing data), a new and simple approach to directly call haplotypes from short-read, paired-end Next Generation Sequencing (NGS) data. To benchmark this method, we considered the APOE classic polymorphism (*1/*2/*3/*4), since it represents one of the best examples of functional polymorphism arising from the haplotype combination of two Single Nucleotide Polymorphisms (SNPs). We leveraged the big Whole Exome Sequencing (WES) and SNP-array data obtained from the multi-ethnic UK BioBank (UKBB, N=48,855). By applying PERHAPS, based on piecing together the paired-end reads according to their FASTQ-labels, we extracted the haplotype data, along with their frequencies and the individual diplotype. Concordance rates between WES directly called diplotypes and the ones generated through statistical pre-phasing and imputation of SNP-array data are extremely high (>99%), either when stratifying the sample by SNP-array genotyping batch or self-reported ethnic group. Hardy-Weinberg Equilibrium tests and the comparison of obtained haplotype frequencies with the ones available from the 1000 Genome Project further supported the reliability of PERHAPS. Notably, we were able to determine the existence of the rare APOE*1 haplotype in two unrelated African subjects from UKBB, supporting its presence at appreciable frequency (approximatively 0.5%) in the African Yoruba population. Despite acknowledging some technical shortcomings, PERHAPS represents a novel and simple approach that will partly overcome the limitations in direct haplotype calling from short read-based sequencing.

Disease-gene association through genome-wide association study (GWAS) is an arduous task for researchers. Investigating single nucleotide polymorphisms that correlate with specific diseases needs statistical analysis of associations. Considering the huge number of possible mutations, in addition to its high cost, another important drawback of GWAS analysis is the large number of false positives. Thus, researchers search for more evidence to cross-check their results through different sources. To provide the researchers with alternative and complementary low-cost disease-gene association evidence, computational approaches come into play. Since molecular networks are able to capture complex interplay among molecules in diseases, they become one of the most extensively used data for disease-gene association prediction. In this survey, we aim to provide a comprehensive and up-to-date review of network-based methods for disease gene prediction. We also conduct an empirical analysis on 14 state-of-the-art methods. To summarize, we first elucidate the task definition for disease gene prediction. Secondly, we categorize existing network-based efforts into network diffusion methods, traditional machine learning methods with handcrafted graph features and graph representation learning methods. Thirdly, an empirical analysis is conducted to evaluate the performance of the selected methods across seven diseases. We also provide distinguishing findings about the discussed methods based on our empirical analysis. Finally, we highlight potential research directions for future studies on disease gene prediction.

INTRODUCTION: Most of the typical chemokine receptors (CKRs) have been identified as coreceptors for a variety of human and simian immunodeficiency viruses (HIVs and SIVs). This study evaluated CCRL2 to examine if it was an HIV/SIV coreceptor. METHODS: The Human glioma cell line, NP-2, is normally resistant to infection by HIV and SIV. The cell was transduced with amplified cluster of differentiation 4 (CD4) as a receptor and CCR5, CXCR4 and CCRL2 as coreceptor candidates to produce NP-2/CD4/coreceptor cells (). The cells were infected with multiplicity of infection (MOI) 1.0. Infected cells were detected by indirect immunofluorescence assay (IFA). Multinucleated giant cells (MGC) in syncytia were quantified by Giemsa staining. Proviral DNA was detected by polymerase chain reaction (PCR), and reverse transcriptase (RT) activity was measured. RESULTS: IFA detected viral antigens of the primary isolates, HIV-1HAN2 and HIV-2MIR in infected NP-2/CD4/CCRL2 cells, indicated CCRL2 as a functional coreceptor. IFA results were confirmed by the detection of proviral DNA and measurement of RT-activity in the spent cell supernatants. Additionally, MGC was detected in HIV-2MIR-infected NP-2/CD4/CCCRL2 cells. HIV-2MIR were found more potent users of CCRL2 than HIV-1HAN2. Moreover, GWAS studies, gene ontology and cell signaling pathways of the HIV-associated genes show interaction of CCRL2 with HIV/SIV envelope protein. CONCLUSIONS: In vitro experiments showed CCRL2 to function as a newly identified coreceptor for primary HIV-2 isolates conveniently. The findings contribute additional insights into HIV/SIV transmission and pathogenesis. However, its in vivo relevance still needs to be evaluated. Confirming in vivo relevance, ligands of CCRL2 can be investigated as potential targets for HIV entry-inhibitor drugs.

Haplotype phasing is a critical step for many genetic applications but incorrect estimates of phase can negatively impact downstream analyses. One proposed strategy to improve phasing accuracy is to combine multiple independent phasing estimates to overcome the limitations of any individual estimate. However, such a strategy is yet to be thoroughly explored. This study provides a comprehensive evaluation of consensus strategies for haplotype phasing. We explore the performance of different consensus paradigms, and the effect of specific constituent tools, across several datasets with different characteristics and their impact on the downstream task of genotype imputation. Based on the outputs of existing phasing tools, we explore two different strategies to construct haplotype consensus estimators: voting across outputs from multiple phasing tools and multiple outputs of a single non-deterministic tool. We find that the consensus approach from multiple tools reduces SE by an average of 10% compared to any constituent tool when applied to European populations and has the highest accuracy regardless of population ethnicity, sample size, variant density or variant frequency. Furthermore, the consensus estimator improves the accuracy of the downstream task of genotype imputation carried out by the widely used Minimac3, pbwt and BEAGLE5 tools. Our results provide guidance on how to produce the most accurate phasing estimates and the trade-offs that a consensus approach may have. Our implementation of consensus haplotype phasing, consHap, is available freely at https://github.com/ziadbkh/consHap. Supplementary information: Supplementary data are available at Briefings in Bioinformatics online.

MOTIVATION: Annotating genetic variants from summary statistics of genome-wide association studies (GWAS) is crucial for predicting risk genes of various disorders. The multimarker analysis of genomic annotation (MAGMA) is one of the most popular tools for this purpose, where MAGMA aggregates signals of single nucleotide polymorphisms (SNPs) to their nearby genes. In biology, SNPs may also affect genes that are far away in the genome, thus missed by MAGMA. Although different upgrades of MAGMA have been proposed to extend gene-wise variant annotations with more information (e.g. Hi-C or eQTL), the regulatory relationships among genes and the tissue specificity of signals have not been taken into account. RESULTS: We propose a new approach, namely network-enhanced MAGMA (nMAGMA), for gene-wise annotation of variants from GWAS summary statistics. Compared with MAGMA and H-MAGMA, nMAGMA significantly extends the lists of genes that can be annotated to SNPs by integrating local signals, long-range regulation signals (i.e. interactions between distal DNA elements), and tissue-specific gene networks. When applied to schizophrenia (SCZ), nMAGMA is able to detect more risk genes (217% more than MAGMA and 57% more than H-MAGMA) that are involved in SCZ compared with MAGMA and H-MAGMA, and more of nMAGMA results can be validated with known SCZ risk genes. Some disease-related functions (e.g. the ATPase pathway in Cortex) are also uncovered in nMAGMA but not in MAGMA or H-MAGMA. Moreover, nMAGMA provides tissue-specific risk signals, which are useful for understanding disorders with multitissue origins.

With the development of high-throughput sequencing technology, the genomic sequences increased exponentially over the last decade. In order to decode these new genomic data, machine learning methods were introduced for genome annotation and analysis. Due to the requirement of most machines learning methods, the biological sequences must be represented as fixed-length digital vectors. In this representation procedure, the physicochemical properties of k-tuple nucleotides are important information. However, the values of the physicochemical properties of k-tuple nucleotides are scattered in different resources. To facilitate the studies on genomic sequences, we developed the first comprehensive database, namely KNIndex (https://knindex.pufengdu.org), for depositing and visualizing physicochemical properties of k-tuple nucleotides. Currently, the KNIndex database contains 182 properties including one for mononucleotide (DNA), 169 for dinucleotide (147 for DNA and 22 for RNA) and 12 for trinucleotide (DNA). KNIndex database also provides a user-friendly web-based interface for the users to browse, query, visualize and download the physicochemical properties of k-tuple nucleotides. With the built-in conversion and visualization functions, users are allowed to display DNA/RNA sequences as curves of multiple physicochemical properties. We wish that the KNIndex will facilitate the related studies in computational biology.

Advances in high-throughput sequencing technologies have resulted in an exponential growth of publicly accessible biological datasets. In the 'big data' driven 'post-genomic' context, much work is being done to explore human protein-protein interactions (PPIs) for a systems level based analysis to uncover useful signals and gain more insights to advance current knowledge and answer specific biological and health questions. These PPIs are experimentally or computationally predicted, stored in different online databases and some of PPI resources are updated regularly. As with many biological datasets, such regular updates continuously render older PPI datasets potentially outdated. Moreover, while many of these interactions are shared between these online resources, each resource includes its own identified PPIs and none of these databases exhaustively contains all existing human PPI maps. In this context, it is essential to enable the integration of or combining interaction datasets from different resources, to generate a PPI map with increased coverage and confidence. To allow researchers to produce an integrated human PPI datasets in real-time, we introduce the integrated human protein-protein interaction network generator (IHP-PING) tool. IHP-PING is a flexible python package which generates a human PPI network from freely available online resources. This tool extracts and integrates heterogeneous PPI datasets to generate a unified PPI network, which is stored locally for further applications.

Circular RNAs (circRNAs) are widely expressed in eukaryotes. The genome-wide interactions between circRNAs and RNA-binding proteins (RBPs) can be probed from cross-linking immunoprecipitation with sequencing data. Therefore, computational methods have been developed for identifying RBP binding sites on circRNAs. Unfortunately, those computational methods often suffer from the low discriminative power of feature representations, numerical instability and poor scalability. To address those limitations, we propose a novel computational method called iCircRBP-DHN using deep hierarchical network for discriminating circRNA-RBP binding sites. The network architecture can be regarded as a deep multi-scale residual network followed by bidirectional gated recurrent units (BiGRUs) with the self-attention mechanism, which can simultaneously extract local and global contextual information. Meanwhile, we propose novel encoding schemes by integrating CircRNA2Vec and the K-tuple nucleotide frequency pattern to represent different degrees of nucleotide dependencies. To validate the effectiveness of our proposed iCircRBP-DHN, we compared its performance with other computational methods on 37 circRNAs datasets and 31 linear RNAs datasets, respectively. The experimental results reveal that iCircRBP-DHN can achieve superior performance over those state-of-the-art algorithms. Moreover, we perform motif analysis on circRNAs bound by those different RBPs, demonstrating that our proposed CircRNA2Vec encoding scheme can be promising. The iCircRBP-DHN method is made available at https://github.com/houzl3416/iCircRBP-DHN.

Cells are compartmentalized by numerous membrane-bounded organelles and membraneless organelles (MLOs) to ensure temporal and spatial regulation of various biological processes. A number of MLOs, such as nucleoli, nuclear speckles and stress granules, exist as liquid droplets within the cells and arise from the condensation of proteins and RNAs via liquid-liquid phase separation (LLPS). By concentrating certain proteins and RNAs, MLOs accelerate biochemical reactions and protect cells during stress, and dysfunction of MLOs is associated with various pathological processes. With the development in this field, more and more relations between the MLOs and diseases have been described; however, these results have not been made available in a centralized resource. Herein, we build MloDisDB, a database which aims to gather the relations between MLOs and diseases from dispersed literature. In addition, the relations between LLPS and diseases were included as well. Currently, MloDisDB contains 771 curated entries from 607 publications; each entry in MloDisDB contains detailed information about the MLO, the disease and the functional factor in the relation. Furthermore, an efficient and user-friendly interface for users to search, browse and download all entries was provided. MloDisDB is the first comprehensive database of the relations between MLOs and diseases so far, and the database is freely accessible at http://mlodis.phasep.pro/.

OBJECTIVE: We aimed to identify key susceptibility gene targets in multiple datasets generated from postmortem brains and blood of Parkinson's disease (PD) patients and healthy controls (HC). METHODS: We performed a multitiered analysis to integrate the gene expression data using multiple-gene chips from 244 human postmortem tissues. We identified hub node genes in the highly PD-related consensus module by constructing protein-protein interaction (PPI) networks. Next, we validated the top four interacting genes in 238 subjects (90 sporadic PD, 125 HC and 23 Parkinson's Plus Syndrome (PPS)). Utilizing multinomial logistic regression analysis (MLRA) and receiver operating characteristic (ROC), we analyzed the risk factors and diagnostic power for discriminating PD from HC and PPS. RESULTS: We identified 1333 genes that were significantly different between PD and HCs based on seven microarray datasets. The identified MEturquoise module is related to synaptic vesicle trafficking (SVT) dysfunction in PD (P < 0.05), and PPI analysis revealed that SVT genes PPP2CA, SYNJ1, NSF and PPP3CB were the top four hub node genes in MEturquoise (P < 0.001). The levels of these four genes in PD postmortem brains were lower than those in HC brains. We found lower blood levels of PPP2CA, SYNJ1 and NSF in PD compared with HC, and lower SYNJ1 in PD compared with PPS (P < 0.05). SYNJ1, negatively correlated to PD severity, displayed an excellent power to discriminating PD from HC and PPS. CONCLUSIONS: This study highlights that SVT genes, especially SYNJ1, may be promising markers in discriminating PD from HCs and PPS.

Angiosarcomas are soft-tissue sarcomas that form malignant vascular tissues. Angiosarcomas are very rare, and due to their aggressive behavior and high metastatic propensity, they have poor clinical outcomes. Hemangiosarcomas commonly occur in domestic dogs, and share pathological and clinical features with human angiosarcomas. Typical pathognomonic features of this tumor are irregular vascular channels that are filled with blood and are lined by a mixture of malignant and nonmalignant endothelial cells. The current gold standard is the histological diagnosis of angiosarcoma; however, microscopic evaluation may be complicated, particularly when tumor cells are undetectable due to the presence of excessive amounts of nontumor cells or when tissue specimens have insufficient tumor content. In this study, we implemented machine learning applications from next-generation transcriptomic data of canine hemangiosarcoma tumor samples (n = 76) and nonmalignant tissues (n = 10) to evaluate their training performance for diagnostic utility. The 10-fold cross-validation test and multiple feature selection methods were applied. We found that extra trees and random forest learning models were the best classifiers for hemangiosarcoma in our testing datasets. We also identified novel gene signatures using the mutual information and Monte Carlo feature selection method. The extra trees model revealed high classification accuracy for hemangiosarcoma in validation sets. We demonstrate that high-throughput sequencing data of canine hemangiosarcoma are trainable for machine learning applications. Furthermore, our approach enables us to identify novel gene signatures as reliable determinants of hemangiosarcoma, providing significant insights into the development of potential applications for this vascular malignancy.

Biological network-based strategies are useful in prioritizing genes associated with diseases. Several comprehensive human gene networks such as STRING, GIANT and HumanNet were developed and used in network-assisted algorithms to identify disease-associated genes. However, none of these networks are disease-specific and may not accurately reflect gene interactions for a specific disease. Aiming to improve disease gene prioritization using networks, we propose a Disease-Specific Network Enhancement Prioritization (DiSNEP) framework. DiSNEP first enhances a comprehensive gene network specifically for a disease through a diffusion process on a gene-gene similarity matrix derived from disease omics data. The enhanced disease-specific gene network thus better reflects true gene interactions for the disease and may improve prioritizing disease-associated genes subsequently. In simulations, DiSNEP that uses an enhanced disease-specific network prioritizes more true signal genes than comparison methods using a general gene network or without prioritization. Applications to prioritize cancer-associated gene expression and DNA methylation signal genes for five cancer types from The Cancer Genome Atlas (TCGA) project suggest that more prioritized candidate genes by DiSNEP are cancer-related according to the DisGeNET database than those prioritized by the comparison methods, consistently across all five cancer types considered, and for both gene expression and DNA methylation signal genes.

Human papillomavirus (HPV) integrating into human genome is the main cause of cervical carcinogenesis. HPV integration selection preference shows strong dependence on local genomic environment. Due to this theory, it is possible to predict HPV integration sites. However, a published bioinformatic tool is not available to date. Thus, we developed an attention-based deep learning model DeepHPV to predict HPV integration sites by learning environment features automatically. In total, 3608 known HPV integration sites were applied to train the model, and 584 reviewed HPV integration sites were used as the testing dataset. DeepHPV showed an area under the receiver-operating characteristic (AUROC) of 0.6336 and an area under the precision recall (AUPR) of 0.5670. Adding RepeatMasker and TCGA Pan Cancer peaks improved the model performance to 0.8464 and 0.8501 in AUROC and 0.7985 and 0.8106 in AUPR, respectively. Next, we tested these trained models on independent database VISDB and found the model adding TCGA Pan Cancer performed better (AUROC: 0.7175, AUPR: 0.6284) than the model adding RepeatMasker peaks (AUROC: 0.6102, AUPR: 0.5577). Moreover, we introduced attention mechanism in DeepHPV and enriched the transcription factor binding sites including BHLHA15, CHR, COUP-TFII, DMRTA2, E2A, HIC1, INR, NPAS, Nr5a2, RARa, SCL, Snail1, Sox10, Sox3, Sox4, Sox6, STAT6, Tbet, Tbx5, TEAD, Tgif2, ZNF189, ZNF416 near attention intensive sites. Together, DeepHPV is a robust and explainable deep learning model, providing new insights into HPV integration preference and mechanism. Availability: DeepHPV is available as an open-source software and can be downloaded from https://github.com/JiuxingLiang/DeepHPV.git, Contact: huzheng1998@163.com, liangjiuxing@m.scnu.edu.cn, lizheyzy@163.com.

BACKGROUND: Whole genome sequencing (WGS) is increasingly used for Mycobacterium tuberculosis (Mtb) research. Countries with the highest tuberculosis (TB) burden face important challenges to integrate WGS into surveillance and research. METHODS: We assessed the global status of Mtb WGS and developed a 3-week training course coupled with long-term mentoring and WGS infrastructure building. Training focused on genome sequencing, bioinformatics and development of a locally relevant WGS research project. The aim of the long-term mentoring was to support trainees in project implementation and funding acquisition. The focus of WGS infrastructure building was on the DNA extraction process and bioinformatics. FINDINGS: Compared to their TB burden, Asia and Africa are grossly underrepresented in Mtb WGS research. Challenges faced resulted in adaptations to the training, mentoring and infrastructure building. Out-of-date laptop hardware and operating systems were overcome by using online tools and a Galaxy WGS analysis pipeline. A case studies approach created a safe atmosphere for students to formulate and defend opinions. Because quality DNA extraction is paramount for WGS, a biosafety level 3 and general laboratory skill training session were added, use of commercial DNA extraction kits was introduced and a 2-week training in a highly equipped laboratory was combined with a 1-week training in the local setting. INTERPRETATION: By developing and sharing the components of and experiences with a sequencing and bioinformatics training program, we hope to stimulate capacity building programs for Mtb WGS and empower high-burden countries to play an important role in WGS-based TB surveillance and research.

Quorum sensing interference (QSI), the disruption and manipulation of quorum sensing (QS) in the dynamic control of bacteria populations could be widely applied in synthetic biology to realize dynamic metabolic control and develop potential clinical therapies. Conventionally, limited QSI molecules (QSIMs) were developed based on molecular structures or for specific QS receptors, which are in short supply for various interferences and manipulations of QS systems. In this study, we developed QSIdb (http://qsidb.lbci.net/), a specialized repository of 633 reported QSIMs and 73 073 expanded QSIMs including both QS agonists and antagonists. We have collected all reported QSIMs in literatures focused on the modifications of N-acyl homoserine lactones, natural QSIMs and synthetic QS analogues. Moreover, we developed a pipeline with SMILES-based similarity assessment algorithms and docking-based validations to mine potential QSIMs from existing 138 805 608 compounds in the PubChem database. In addition, we proposed a new measure, pocketedit, for assessing the similarities of active protein pockets or QSIMs crosstalk, and obtained 273 possible potential broad-spectrum QSIMs. We provided user-friendly browsing and searching facilities for easy data retrieval and comparison. QSIdb could assist the scientific community in understanding QS-related therapeutics, manipulating QS-based genetic circuits in metabolic engineering, developing potential broad-spectrum QSIMs and expanding new ligands for other receptors.

MOTIVATION: The advancements of single-cell sequencing methods have paved the way for the characterization of cellular states at unprecedented resolution, revolutionizing the investigation on complex biological systems. Yet, single-cell sequencing experiments are hindered by several technical issues, which cause output data to be noisy, impacting the reliability of downstream analyses. Therefore, a growing number of data science methods has been proposed to recover lost or corrupted information from single-cell sequencing data. To date, however, no quantitative benchmarks have been proposed to evaluate such methods. RESULTS: We present a comprehensive analysis of the state-of-the-art computational approaches for denoising and imputation of single-cell transcriptomic data, comparing their performance in different experimental scenarios. In detail, we compared 19 denoising and imputation methods, on both simulated and real-world datasets, with respect to several performance metrics related to imputation of dropout events, recovery of true expression profiles, characterization of cell similarity, identification of differentially expressed genes and computation time. The effectiveness and scalability of all methods were assessed with regard to distinct sequencing protocols, sample size and different levels of biological variability and technical noise. As a result, we identify a subset of versatile approaches exhibiting solid performances on most tests and show that certain algorithmic families prove effective on specific tasks but inefficient on others. Finally, most methods appear to benefit from the introduction of appropriate assumptions on noise distribution of biological processes.

Despite impressive improvement in the next-generation sequencing technology, reliable detection of indels is still a difficult endeavour. Recognition of true indels is of prime importance in many applications, such as personalized health care, disease genomics and population genetics. Recently, advanced machine learning techniques have been successfully applied to classification problems with large-scale data. In this paper, we present SICaRiO, a gradient boosting classifier for the reliable detection of true indels, trained with the gold-standard dataset from 'Genome in a Bottle' (GIAB) consortium. Our filtering scheme significantly improves the performance of each variant calling pipeline used in GIAB and beyond. SICaRiO uses genomic features that can be computed from publicly available resources, i.e. it does not require sequencing pipeline-specific information (e.g. read depth). This study also sheds lights on prior genomic contexts responsible for the erroneous calling of indels made by sequencing pipelines. We have compared prediction difficulty for three categories of indels over different sequencing pipelines. We have also ranked genomic features according to their predictivity in determining false positives.

Causal molecular interactions represent key building blocks used in computational modeling, where they facilitate the assembly of regulatory networks. Logical regulatory networks can be used to predict biological and cellular behaviors by system perturbations and in silico simulations. Today, broad sets of causal interactions are available in a variety of biological knowledge resources. However, different visions, based on distinct biological interests, have led to the development of multiple ways to describe and annotate causal molecular interactions. It can therefore be challenging to efficiently explore various resources of causal interaction and maintain an overview of recorded contextual information that ensures valid use of the data. This review lists the different types of public resources with causal interactions, the different views on biological processes that they represent, the various data formats they use for data representation and storage, and the data exchange and conversion procedures that are available to extract and download these interactions. This may further raise awareness among the targeted audience, i.e. logical modelers and other scientists interested in molecular causal interactions, but also database managers and curators, about the abundance and variety of causal molecular interaction data, and the variety of tools and approaches to convert them into one interoperable resource.

The size and quality of chemical libraries to the drug discovery pipeline are crucial for developing new drugs or repurposing existing drugs. Existing techniques such as combinatorial organic synthesis and high-throughput screening usually make the process extraordinarily tough and complicated since the search space of synthetically feasible drugs is exorbitantly huge. While reinforcement learning has been mostly exploited in the literature for generating novel compounds, the requirement of designing a reward function that succinctly represents the learning objective could prove daunting in certain complex domains. Generative adversarial network-based methods also mostly discard the discriminator after training and could be hard to train. In this study, we propose a framework for training a compound generator and learn a transferable reward function based on the entropy maximization inverse reinforcement learning (IRL) paradigm. We show from our experiments that the IRL route offers a rational alternative for generating chemical compounds in domains where reward function engineering may be less appealing or impossible while data exhibiting the desired objective is readily available.

Plant transcriptome encompasses numerous endogenous, regulatory non-coding RNAs (ncRNAs) that play a major biological role in regulating key physiological mechanisms. While studies have shown that ncRNAs are extremely diverse and ubiquitous, the functions of the vast majority of ncRNAs are still unknown. With ever-increasing ncRNAs under study, it is essential to identify, categorize and annotate these ncRNAs on a genome-wide scale. The use of high-throughput RNA sequencing (RNA-seq) technologies provides a broader picture of the non-coding component of transcriptome, enabling the comprehensive identification and annotation of all major ncRNAs across samples. However, the detection of known and emerging class of ncRNAs from RNA-seq data demands complex computational methods owing to their unique as well as similar characteristics. Here, we discuss major plant endogenous, regulatory ncRNAs in an RNA sample followed by computational strategies applied to discover each class of ncRNAs using RNA-seq. We also provide a collection of relevant software packages and databases to present a comprehensive bioinformatics toolbox for plant ncRNA researchers. We assume that the discussions in this review will provide a rationale for the discovery of all major categories of plant ncRNAs.

CyanoPATH is a database that curates and analyzes the common genomic functional repertoire for cyanobacteria harmful algal blooms (CyanoHABs) in eutrophic waters. Based on the literature of empirical studies and genome/protein databases, it summarizes four types of information: common biological functions (pathways) driving CyanoHABs, customized pathway maps, classification of blooming type based on databases and the genomes of cyanobacteria. A total of 19 pathways are reconstructed, which are involved in the utilization of macronutrients (e.g. carbon, nitrogen, phosphorus and sulfur), micronutrients (e.g. zinc, magnesium, iron, etc.) and other resources (e.g. light and vitamins) and in stress resistance (e.g. lead and copper). These pathways, comprised of both transport and biochemical reactions, are reconstructed with proteins from NCBI and reactions from KEGG and visualized with self-created transport/reaction maps. The pathways are hierarchical and consist of subpathways, protein/enzyme complexes and constituent proteins. New cyanobacterial genomes can be annotated and visualized for these pathways and compared with existing species. This set of genomic functional repertoire is useful in analyzing aquatic metagenomes and metatranscriptomes in CyanoHAB research. Most importantly, it establishes a link between genome and ecology. All these reference proteins, pathways and maps and genomes are free to download at http://www.csbg-jlu.info/CyanoPATH.

Recombination is one of the most important molecular mechanisms of prokaryotic genome evolution, but its exact roles are still in debate. Here we try to infer genome-wide recombination within a species, utilizing a dataset of 149 complete genomes of Escherichia coli from diverse animal hosts and geographic origins, including 45 in-house sequenced with the single-molecular real-time platform. Two major clades identified based on physiological, clinical and ecological characteristics form distinct genetic lineages based on scarcity of interclade gene exchanges. By defining gene-based syntenies for genomic segments within and between the two clades, we build a fine-scale recombination map for this representative global E. coli population. The map suggests extensive within-clade recombination that often breaks physical linkages among individual genes but seldom interrupts the structure of genome organizational frameworks as well as primary metabolic portfolios supported by the framework integrity, possibly due to strong natural selection for both physiological compatibility and ecological fitness. In contrast, the between-clade recombination declines drastically when phylogenetic distance increases to the extent where a 10-fold reduction can be observed, establishing a firm genetic barrier between clades. Our empirical data suggest a critical role for such recombination events in the early stage of speciation where recombination rate is associated with phylogenetic distance in addition to sequence and gene variations. The extensive intraclade recombination binds sister strains into a quasisexual group and optimizes genes or alleles to streamline physiological activities, whereas the sharply declined interclade recombination split the population into clades adaptive to divergent ecological niches.

Developmental pluripotency-associated 2 (Dppa2) and developmental pluripotency-associated 4 (Dppa4) as positive drivers were helpful for transcriptional regulation of zygotic genome activation (ZGA). Here, we systematically assessed the cooperative interplay of Dppa2 and Dppa4 in regulating cell pluripotency and found that simultaneous overexpression of Dppa2/4 can make induced pluripotent stem cells closer to embryonic stem cells (ESCs). Compared with other pluripotency transcription factors, Dppa2/4 can regulate majorities of signaling pathways by binding on CG-rich region of proximal promoter (0-500 bp), of which 85% and 77% signaling pathways were significantly activated by Dppa2 and Dppa4, respectively. Notably, Dppa2/4 also can dramatically trigger the decisive signaling pathways for facilitating ZGA, including Hippo, MAPK and TGF-beta signaling pathways and so on. At last, we found alkaline phosphatase, placental-like 2 (Alppl2) was completely silenced when Dppa2 and 4 single- or double-knockout in ESC, which is consistent with Dux. Moreover, Alppl2 was significantly activated in mouse 2-cell embryos and 4-8 cells stage of human embryos, further predicted that Alppl2 was directly regulated by Dppa2/4 as a ZGA candidate driver to facilitate pre-embryonic development.

Protein-carbohydrate interactions play a major role in several cellular and biological processes. Elucidating the factors influencing the binding affinity of protein-carbohydrate complexes and predicting their free energy of binding provide deep insights for understanding the recognition mechanism. In this work, we have collected the experimental binding affinity data for a set of 389 protein-carbohydrate complexes and derived several structure-based features such as contact potentials, interaction energy, number of binding residues and contacts between different types of atoms. Our analysis on the relationship between binding affinity and structural features revealed that the important factors depend on the type of the complex based on number of carbohydrate and protein chains. Specifically, binding site residues, accessible surface area, interactions between various atoms and energy contributions are important to understand the binding affinity. Further, we have developed multiple regression equations for predicting the binding affinity of protein-carbohydrate complexes belonging to six categories of protein-carbohydrate complexes. Our method showed an average correlation and mean absolute error of 0.731 and 1.149 kcal/mol, respectively, between experimental and predicted binding affinities on a jackknife test. We have developed a web server PCA-Pred, Protein-Carbohydrate Affinity Predictor, for predicting the binding affinity of protein-carbohydrate complexes. The web server is freely accessible at https://web.iitm.ac.in/bioinfo2/pcapred/. The web server is implemented using HTML and Python and supports recent versions of major browsers such as Chrome, Firefox, IE10 and Opera.

Although long noncoding RNAs (lncRNAs) have significant tissue specificity, their expression and variability in single cells remain unclear. Here, we developed ColorCells (http://rna.sysu.edu.cn/colorcells/), a resource for comparative analysis of lncRNAs expression, classification and functions in single-cell RNA-Seq data. ColorCells was applied to 167 913 publicly available scRNA-Seq datasets from six species, and identified a batch of cell-specific lncRNAs. These lncRNAs show surprising levels of expression variability between different cell clusters, and has the comparable cell classification ability as known marker genes. Cell-specific lncRNAs have been identified and further validated by in vitro experiments. We found that lncRNAs are typically co-expressed with the mRNAs in the same cell cluster, which can be used to uncover lncRNAs' functions. Our study emphasizes the need to uncover lncRNAs in all cell types and shows the power of lncRNAs as novel marker genes at single cell resolution.

The protein Yin Yang 1 (YY1) could form dimers that facilitate the interaction between active enhancers and promoter-proximal elements. YY1-mediated enhancer-promoter interaction is the general feature of mammalian gene control. Recently, some computational methods have been developed to characterize the interactions between DNA elements by elucidating important features of chromatin folding; however, no computational methods have been developed for identifying the YY1-mediated chromatin loops. In this study, we developed a deep learning algorithm named DeepYY1 based on word2vec to determine whether a pair of YY1 motifs would form a loop. The proposed models showed a high prediction performance (AUCs$\ge$0.93) on both training datasets and testing datasets in different cell types, demonstrating that DeepYY1 has an excellent performance in the identification of the YY1-mediated chromatin loops. Our study also suggested that sequences play an important role in the formation of YY1-mediated chromatin loops. Furthermore, we briefly discussed the distribution of the replication origin site in the loops. Finally, a user-friendly web server was established, and it can be freely accessed at http://lin-group.cn/server/DeepYY1.

Leaf senescence is a highly complex, genetically regulated and well-ordered process with multiple layers and pathways. Delaying leaf senescence would help increase grain yields in rice. Over the past 15 years, more than 100 rice leaf-senescence genes have been cloned, greatly improving the understanding of leaf senescence in rice. Systematically elucidating the molecular mechanisms underlying leaf senescence will provide breeders with new tools/options for improving many important agronomic traits. In this study, we summarized recent reports on 125 rice leaf-senescence genes, providing an overview of the research progress in this field by analyzing the subcellular localizations, molecular functions and the relationship of them. These data showed that chlorophyll synthesis and degradation, chloroplast development, abscisic acid pathway, jasmonic acid pathway, nitrogen assimilation and ROS play an important role in regulating the leaf senescence in rice. Furthermore, we predicted and analyzed the proteins that interact with leaf-senescence proteins and achieved a more profound understanding of the molecular principles underlying the regulatory mechanisms by which leaf senescence occurs, thus providing new insights for future investigations of leaf senescence in rice.

AlgPred 2.0 is a web server developed for predicting allergenic proteins and allergenic regions in a protein. It is an updated version of AlgPred developed in 2006. The dataset used for training, testing and validation consists of 10 075 allergens and 10 075 non-allergens. In addition, 10 451 experimentally validated immunoglobulin E (IgE) epitopes were used to identify antigenic regions in a protein. All models were trained on 80% of data called training dataset, and the performance of models was evaluated using 5-fold cross-validation technique. The performance of the final model trained on the training dataset was evaluated on 20% of data called validation dataset; no two proteins in any two sets have more than 40% similarity. First, a Basic Local Alignment Search Tool (BLAST) search has been performed against the dataset, and allergens were predicted based on the level of similarity with known allergens. Second, IgE epitopes obtained from the IEDB database were searched in the dataset to predict allergens based on their presence in a protein. Third, motif-based approaches like multiple EM for motif elicitation/motif alignment and search tool have been used to predict allergens. Fourth, allergen prediction models have been developed using a wide range of machine learning techniques. Finally, the ensemble approach has been used for predicting allergenic protein by combining prediction scores of different approaches. Our best model achieved maximum performance in terms of area under receiver operating characteristic curve 0.98 with Matthew's correlation coefficient 0.85 on the validation dataset. A web server AlgPred 2.0 has been developed that allows the prediction of allergens, mapping of IgE epitope, motif search and BLAST search (https://webs.iiitd.edu.in/raghava/algpred2/).

Cell-cell communications in multicellular organisms generally involve secreted ligand-receptor (LR) interactions, which is vital for various biological phenomena. Recent advancements in single-cell RNA sequencing (scRNA-seq) have effectively resolved cellular phenotypic heterogeneity and the cell-type composition of complex tissues, facilitating the systematic investigation of cell-cell communications at single-cell resolution. However, assessment of chemical-signal-dependent cell-cell communication through scRNA-seq relies heavily on prior knowledge of LR interaction pairs. We constructed CellTalkDB (http://tcm.zju.edu.cn/celltalkdb), a manually curated comprehensive database of LR interaction pairs in humans and mice comprising 3398 human LR pairs and 2033 mouse LR pairs, through text mining and manual verification of known protein-protein interactions using the STRING database, with literature-supported evidence for each pair. Compared with SingleCellSignalR, the largest LR-pair resource, CellTalkDB includes not only 2033 mouse LR pairs but also 377 additional human LR pairs. In conclusion, the data on human and mouse LR pairs contained in CellTalkDB could help to further the inference and understanding of the LR-interaction-based cell-cell communications, which might provide new insights into the mechanism underlying biological processes.

MOTIVATION: Computational methods accelerate drug discovery and play an important role in biomedicine, such as molecular property prediction and compound-protein interaction (CPI) identification. A key challenge is to learn useful molecular representation. In the early years, molecular properties are mainly calculated by quantum mechanics or predicted by traditional machine learning methods, which requires expert knowledge and is often labor-intensive. Nowadays, graph neural networks have received significant attention because of the powerful ability to learn representation from graph data. Nevertheless, current graph-based methods have some limitations that need to be addressed, such as large-scale parameters and insufficient bond information extraction. RESULTS: In this study, we proposed a graph-based approach and employed a novel triplet message mechanism to learn molecular representation efficiently, named triplet message networks (TrimNet). We show that TrimNet can accurately complete multiple molecular representation learning tasks with significant parameter reduction, including the quantum properties, bioactivity, physiology and CPI prediction. In the experiments, TrimNet outperforms the previous state-of-the-art method by a significant margin on various datasets. Besides the few parameters and high prediction accuracy, TrimNet could focus on the atoms essential to the target properties, providing a clear interpretation of the prediction tasks. These advantages have established TrimNet as a powerful and useful computational tool in solving the challenging problem of molecular representation learning. AVAILABILITY: The quantum and drug datasets are available on the website of MoleculeNet: http://moleculenet.ai. The source code is available in GitHub: https://github.com/yvquanli/trimnet. CONTACT: xjyao@lzu.edu.cn, songsen@tsinghua.edu.cn.

The triangular correlation heatmap aiming to visualize the linkage disequilibrium (LD) pattern and haplotype block structure of SNPs is ubiquitous component of population-based genetic studies. However, current tools suffered from the problem of time and memory consuming. Here, we developed LDBlockShow, an open source software, for visualizing LD and haplotype blocks from variant call format files. It is time and memory saving. In a test dataset with 100 SNPs from 60 000 subjects, it was at least 10.60 times faster and used only 0.03-13.33% of physical memory as compared with other tools. In addition, it could generate figures that simultaneously display additional statistical context (e.g. association P-values) and genomic region annotations. It can also compress the SVG files with a large number of SNPs and support subgroup analysis. This fast and convenient tool will facilitate the visualization of LD and haplotype blocks for geneticists.

Enhancer-promoter interactions (EPIs) play an important role in transcriptional regulation. Recently, machine learning-based methods have been widely used in the genome-scale identification of EPIs due to their promising predictive performance. In this paper, we propose a novel method, termed EPI-DLMH, for predicting EPIs with the use of DNA sequences only. EPI-DLMH consists of three major steps. First, a two-layer convolutional neural network is used to learn local features, and an bidirectional gated recurrent unit network is used to capture long-range dependencies on the sequences of promoters and enhancers. Second, an attention mechanism is used for focusing on relatively important features. Finally, a matching heuristic mechanism is introduced for the exploration of the interaction between enhancers and promoters. We use benchmark datasets in evaluating and comparing the proposed method with existing methods. Comparative results show that our model is superior to currently existing models in multiple cell lines. Specifically, we found that the matching heuristic mechanism introduced into the proposed model mainly contributes to the improvement of performance in terms of overall accuracy. Additionally, compared with existing models, our model is more efficient with regard to computational speed.

Sequencing technologies have led to the identification of many variants in the human genome which could act as disease-drivers. As a consequence, a variety of bioinformatics tools have been proposed for predicting which variants may drive disease, and which may be causatively neutral. After briefly reviewing generic tools, we focus on a subset of these methods specifically geared toward predicting which variants in the human cancer genome may act as enablers of unregulated cell proliferation. We consider the resultant view of the cancer genome indicated by these predictors and discuss ways in which these types of prediction tools may be progressed by further research.

In viruses, posttranslational modifications (PTMs) are essential for their life cycle. Recognizing viral PTMs is very important for a better understanding of the mechanism of viral infections and finding potential drug targets. However, few studies have investigated the roles of viral PTMs in virus-human interactions using comprehensive viral PTM datasets. To fill this gap, we developed the first comprehensive viral posttranslational modification database (VPTMdb) for collecting systematic information of PTMs in human viruses and infected host cells. The VPTMdb contains 1240 unique viral PTM sites with 8 modification types from 43 viruses (818 experimentally verified PTM sites manually extracted from 150 publications and 422 PTMs extracted from SwissProt) as well as 13 650 infected cells' PTMs extracted from seven global proteomics experiments in six human viruses. The investigation of viral PTM sequences motifs showed that most viral PTMs have the consensus motifs with human proteins in phosphorylation and five cellular kinase families phosphorylate more than 10 viral species. The analysis of protein disordered regions presented that more than 50% glycosylation sites of double-strand DNA viruses are in the disordered regions, whereas single-strand RNA and retroviruses prefer ordered regions. Domain-domain interaction analysis indicating potential roles of viral PTMs play in infections. The findings should make an important contribution to the field of virus-human interaction. Moreover, we created a novel sequence-based classifier named VPTMpre to help users predict viral protein phosphorylation sites. VPTMdb online web server (http://vptmdb.com:8787/VPTMdb/) was implemented for users to download viral PTM data and predict phosphorylation sites of interest.

Although great progress has been made in prognostic outcome prediction, small sample size remains a challenge in obtaining accurate and robust classifiers. We proposed the Rescaled linear square Regression based Least Squares Learning (RRLSL), a jointly developed semi-supervised feature selection and classifier, for predicting prognostic outcome of cancer patients. RRLSL used the least square regression to identify the scale factors and then rank the features in available multiple types of molecular data. We applied the unlabeled multiple molecular data in conjunction with the labeled data to develop a similarity graph. RRLSL produced the constraint with kernel functions to bridge the gap between label information and geometry information from messenger RNA and microRNA expression profiling. Importantly, this semi-supervised model proposed the least squares learning with L2 regularization to develop a semi-supervised classifier. RRLSL suggested the performance improvement in the prognostic outcome prediction and successfully discriminated between the recurrent patients and non-recurrent ones. We also demonstrated that RRLSL improved the accuracy and Area Under the Precision Recall Curve (AUPRC) as compared to the baseline semi-supervised methods. RRLSL is available for a stand-alone software package (https://github.com/ShiMGLab/RRLSL). A short abstract We proposed the Rescaled linear square Regression based Least Squares Learning (RRLSL), a jointly developed semi-supervised feature selection and classifier, for predicting prognostic outcome of cancer patients. RRLSL used the least square regression to identify the scale factors to rank the features in available multiple types of molecular data. RRLSL produced the constraint with kernel functions to bridge the gap between label information and geometry information from messenger RNA and microRNA expression profiling. Importantly, this semi-supervised model proposed the least squares learning with L2 regularization to develop the semi-supervised classifier. RRLSL suggested the performance improvement in the prognostic outcome prediction and successfully discriminated between the recurrent patients and non-recurrent ones.

In order to extract useful information from a huge amount of biological data nowadays, simple and convenient tools are urgently needed for data analysis and modeling. In this paper, an automatic data mining tool, termed as ABCModeller (Automatic Binary Classification Modeller), with a user-friendly graphical interface was developed here, which includes automated functions as data preprocessing, significant feature extraction, classification modeling, model evaluation and prediction. In order to enhance the generalization ability of the final model, a consistent voting method was built here in this tool with the utilization of three popular machine-learning algorithms, as artificial neural network, support vector machine and random forest. Besides, Fibonacci search and orthogonal experimental design methods were also employed here to automatically select significant features in the data space and optimal hyperparameters of the three algorithms to achieve the best model. The reliability of this tool has been verified through multiple benchmark data sets. In addition, with the advantage of a user-friendly graphical interface of this tool, users without any programming skills can easily obtain reliable models directly from original data, which can reduce the complexity of modeling and data mining, and contribute to the development of related research including but not limited to biology. The excitable file of this tool can be downloaded from http://lishuyan.lzu.edu.cn/ABCModeller.rar.

Delineating the fingerprint or feature vector of a receptor/protein will facilitate the structural and biological studies, as well as the rational design and development of drugs with high affinities and selectivity. However, protein is complicated by its different functional regions that can bind to some of its protein partner(s), substrate(s), orthosteric ligand(s) or allosteric modulator(s) where cogent methods like molecular fingerprints do not work well. We here elaborate a scoring-function-based computing protocol Molecular Complex Characterizing System to help characterize the binding feature of protein-ligand complexes. Based on the reported receptor-ligand interactions, we first quantitate the energy contribution of each individual residue which may be an alternative of MD-based energy decomposition. We then construct a vector for the energy contribution to represent the pattern of the ligand recognition at a receptor and qualitatively analyze the matching level with other receptors. Finally, the energy contribution vector is explored for extensive use in similarity and clustering. The present work provides a new approach to cluster proteins, a perspective counterpart for determining the protein characteristics in the binding, and an advanced screening technique where molecular docking is applicable.

MOTIVATION: The functional changes of the genes, RNAs and proteins will eventually be reflected in the metabolic level. Increasing number of researchers have researched mechanism, biomarkers and targeted drugs by metabolites. However, compared with our knowledge about genes, RNAs, and proteins, we still know few about diseases-related metabolites. All the few existed methods for identifying diseases-related metabolites ignore the chemical structure of metabolites, fail to recognize the association pattern between metabolites and diseases, and fail to apply to isolated diseases and metabolites. RESULTS: In this study, we present a graph deep learning based method, named Deep-DRM, for identifying diseases-related metabolites. First, chemical structures of metabolites were used to calculate similarities of metabolites. The similarities of diseases were obtained based on their functional gene network and semantic associations. Therefore, both metabolites and diseases network could be built. Next, Graph Convolutional Network (GCN) was applied to encode the features of metabolites and diseases, respectively. Then, the dimension of these features was reduced by Principal components analysis (PCA) with retainment 99% information. Finally, Deep neural network was built for identifying true metabolite-disease pairs (MDPs) based on these features. The 10-cross validations on three testing setups showed outstanding AUC (0.952) and AUPR (0.939) of Deep-DRM compared with previous methods and similar approaches. Ten of top 15 predicted associations between diseases and metabolites got support by other studies, which suggests that Deep-DRM is an efficient method to identify MDPs. CONTACT: liangcheng@hrbmu.edu.cn. AVAILABILITY AND IMPLEMENTATION: https://github.com/zty2009/GPDNN-for-Identify-ing-Disease-related-Metabolites.

MOTIVATION: DNA methylation is a biological process impacting the gene functions without changing the underlying DNA sequence. The DNA methylation machinery usually attaches methyl groups to some specific cytosine residues, which modify the chromatin architectures. Such modifications in the promoter regions will inactivate some tumor-suppressor genes. DNA methylation within the coding region may significantly reduce the transcription elongation efficiency. The gene function may be tuned through some cytosines are methylated. METHODS: This study hypothesizes that the overall methylation level across a gene may have a better association with the sample labels like diseases than the methylations of individual cytosines. The gene methylation level is formulated as a regression model using the methylation levels of all the cytosines within this gene. A comprehensive evaluation of various feature selection algorithms and classification algorithms is carried out between the gene-level and residue-level methylation levels. RESULTS: A comprehensive evaluation was conducted to compare the gene and cytosine methylation levels for their associations with the sample labels and classification performances. The unsupervised clustering was also improved using the gene methylation levels. Some genes demonstrated statistically significant associations with the class label, even when no residue-level methylation features have statistically significant associations with the class label. So in summary, the trained gene methylation levels improved various methylome-based machine learning models. Both methodology development of regression algorithms and experimental validation of the gene-level methylation biomarkers are worth of further investigations in the future studies. The source code, example data files and manual are available at http://www.healthinformaticslab.org/supp/.

DNA/RNA motif mining is the foundation of gene function research. The DNA/RNA motif mining plays an extremely important role in identifying the DNA- or RNA-protein binding site, which helps to understand the mechanism of gene regulation and management. For the past few decades, researchers have been working on designing new efficient and accurate algorithms for mining motif. These algorithms can be roughly divided into two categories: the enumeration approach and the probabilistic method. In recent years, machine learning methods had made great progress, especially the algorithm represented by deep learning had achieved good performance. Existing deep learning methods in motif mining can be roughly divided into three types of models: convolutional neural network (CNN) based models, recurrent neural network (RNN) based models, and hybrid CNN-RNN based models. We introduce the application of deep learning in the field of motif mining in terms of data preprocessing, features of existing deep learning architectures and comparing the differences between the basic deep learning models. Through the analysis and comparison of existing deep learning methods, we found that the more complex models tend to perform better than simple ones when data are sufficient, and the current methods are relatively simple compared with other fields such as computer vision, language processing (NLP), computer games, etc. Therefore, it is necessary to conduct a summary in motif mining by deep learning, which can help researchers understand this field.

Deep generative models can be trained to represent the joint distribution of data, such as measurements of single nucleotide polymorphisms (SNPs) from several individuals. Subsequently, synthetic observations are obtained by drawing from this distribution. This has been shown to be useful for several tasks, such as removal of noise, imputation, for better understanding underlying patterns, or even exchanging data under privacy constraints. Yet, it is still unclear how well these approaches work with limited sample size. We investigate such settings specifically for binary data, e.g. as relevant when considering SNP measurements, and evaluate three frequently employed generative modeling approaches, variational autoencoders (VAEs), deep Boltzmann machines (DBMs) and generative adversarial networks (GANs). This includes conditional approaches, such as when considering gene expression conditional on SNPs. Recovery of pair-wise odds ratios (ORs) is considered as a primary performance criterion. For simulated as well as real SNP data, we observe that DBMs generally can recover structure for up to 300 variables, with a tendency of over-estimating ORs when not carefully tuned. VAEs generally get the direction and relative strength of pairwise relations right, yet with considerable under-estimation of ORs. GANs provide stable results only with larger sample sizes and strong pair-wise relations in the data. Taken together, DBMs and VAEs (in contrast to GANs) appear to be well suited for binary omics data, even at rather small sample sizes. This opens the way for many potential applications where synthetic observations from omics data might be useful.